key
stringlengths 7
86
| messages
listlengths 1
1
| ground_truth
stringlengths 62
280k
| dataset
stringclasses 1
value | constraint_type
stringclasses 1
value | constraint
stringlengths 31
956
|
|---|---|---|---|---|---|
personahub_ibq27zn7jomyezjmar41j41w | [
{
"content": "Write a python function to parse a list of dictionaries representing potential grants and funding opportunities for a local farmer. Each dictionary contains the 'name' of the grant, 'amount' of funding available, and a 'deadline' date in the format 'YYYY-MM-DD'. The function should return a list of names of grants that are still available based on a given date input. The function should take two inputs: \n\n1. A list of dictionaries, where each dictionary has keys 'name', 'amount', and 'deadline'.\n2. A string representing the current date in the format 'YYYY-MM-DD'.\n\nThe output should be a list of grant names whose deadline is after the given current date.\n\nExample:\n\nInput:\n```python\ngrants = [\n {'name': 'Sustainable Farming Grant', 'amount': 5000, 'deadline': '2023-12-31'},\n {'name': 'Organic Growth Fund', 'amount': 3000, 'deadline': '2023-11-15'},\n {'name': 'Local Produce Support', 'amount': 2000, 'deadline': '2023-10-10'}\n]\ncurrent_date = '2023-11-01'\n```\n\nExpected Output:\n```python\n['Sustainable Farming Grant', 'Organic Growth Fund']\n``` Your answer must contain exactly 10 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 Wrap your entire response with double quotation marks. Do not include keywords ['consequence', 'database', 'dependent', 'make'] in the response. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_bullet_lists', 'startend:quotation', 'keywords:forbidden_words', 'startend:quotation'], 'kwargs': [{'num_bullets': 10}, None, {'forbidden_words': ['consequence', 'database', 'dependent', 'make']}, None]}] | ifeval | multi | Your answer must contain exactly 10 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Wrap your entire response with double quotation marks. Do not include keywords ['consequence', 'database', 'dependent', 'make'] in the response. Wrap your entire response with double quotation marks. |
personahub_soy7rcvj8n8nnub2vt0cg0uo | [
{
"content": "Provide a detailed analysis of the renewable energy sector's growth in the last decade, ensuring each paragraph contains at least 20 words starting with the letter 'R'. Conclude the report with the phrase 'Investment potential confirmed!'. Your answer must contain exactly 2 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_bullet_lists'], 'kwargs': [{'num_bullets': 2}]}] | ifeval | multi | Your answer must contain exactly 2 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 |
science.drug_combo_extraction_re.1310 | [
{
"content": "You will be shown a paragraph from a biomedical research article. Your task is to extract all drug combinations appearing in a specific sentence within in the paragraph. Each drug combination should be assigned to one of the following three categories:\n\n- POS: Indicates a positive interaction between the drugs in the combination; for instance, drugs that have an additive or synergistic effect.\n- NEG: Indicates a negative interaction between the drugs in the combination; for instance, combining these drugs might result in adverse side effects, or might reduce their efficacy.\n- COMB: Indicates that the drugs are given in combination, but the type of interaction between the drugs cannot be determined based on the provided context.\n\nPlease format your answer as a json array. Each entry in the array should itself be an array formatted as [<drug_1>, <drug_2>, ..., <drug_n>, <category>] where <category> is one of the three categories listed above and <drug_1>, ..., <drug_n> are drug names copied verbatim from the input sentence. Different combinations may involve different numbers of drugs; in other words, the `n` in <drug_n> may vary.\n\nAs an example, the following output describes two extracted drug combinations; one between two drugs, and one between three drugs:\n\n[[\"artesunate\", \"artemether\", \"COMB\"], [\"Nifedipine\", \"Labetalol\", \"Prazosin\", \"POS\"]]\n\nThe paragraph and specific sentence are below. You should only extract relationships expressed in the specific sentence; the paragraph is provided for context.\n\nIn your output, return only the json array and no other text. If no drug combinations appear, return an empty array `[]`.\n\nparagraph: Pancreatic cancer: from state-of-the-art treatments to promising novel therapies. Pancreatic cancer is expected to be the second deadliest malignancy in the USA by 2020. The survival rates for patients with other gastrointestinal malignancies have increased consistently during the past 30 years; unfortunately, however, the outcomes of patients with pancreatic cancer have not changed significantly. Although surgery remains the only curative treatment for pancreatic cancer, therapeutic strategies based on initial resection have not substantially improved the survival of patients with resectable disease over the past 25 years; presently, more than 80% of patients suffer disease relapse after resection. Preclinical evidence that pancreatic cancer is a systemic disease suggests a possible benefit for early administration of systemic therapy in these patients. In locally advanced disease, the role of chemoradiotherapy is increasingly being questioned, particularly considering the results of the LAP-07 trial. Novel biomarkers are clearly needed to identify subsets of patients likely to benefit from chemoradiotherapy. In the metastatic setting , FOLFIRINOX ( folinic acid , 5-fluorouracil , irinotecan , and oxaliplatin ) , and nab-paclitaxel plus gemcitabine have yielded only modest improvements in survival . Thus, new treatments are urgently needed for patients with pancreatic cancer. Herein, we review the state-of-the-art of pancreatic cancer treatment, and the upcoming novel therapeutics that hold promise in this disease are also discussed.\n\nsentence: In the metastatic setting , FOLFIRINOX ( folinic acid , 5-fluorouracil , irinotecan , and oxaliplatin ) , and nab-paclitaxel plus gemcitabine have yielded only modest improvements in survival . Include keywords ['call', 'challenge', 'gift', 'positive'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence'], 'kwargs': [{'keywords': ['call', 'challenge', 'gift', 'positive']}]}] | ifeval | multi | Include keywords ['call', 'challenge', 'gift', 'positive'] in the response. |
personahub_6ay19shhsizu6gvo6h28iisg | [
{
"content": "A seasoned interactive media producer has been analyzing user engagement data for an award-winning interactive documentary. The documentary consists of a series of interconnected scenes, each with multiple interactive elements that influence the user's experience and choices.\n\n1. Define a directed graph \\( G = (V, E) \\) where each vertex \\( v \\in V \\) represents a scene, and each directed edge \\( e \\in E \\) represents a possible transition between scenes due to user interaction. Given that the graph has 10 vertices and 20 edges, calculate the number of possible Eulerian paths in the graph. Recall that an Eulerian path visits every edge exactly once. \n\n2. The producer is also analyzing the time users spend on interactive elements within each scene. Suppose the average time spent on each interactive element in scene \\( S_i \\) follows a normal distribution with a mean \\( \\mu_i \\) and standard deviation \\( \\sigma_i \\). If each of the 10 scenes has an average interaction time described by \\( \\mu_i = 5 + i \\) and \\( \\sigma_i = \\sqrt{i} \\) for \\( i = 1, 2, \\ldots, 10 \\), calculate the probability that a user spends more than 7 minutes on a random interactive element in scene \\( S_5 \\). Your ENTIRE response should be in Spanish language, no other language is allowed. Your response should contain at least 20 sentences. Include keywords ['familiar', 'ladder', 'push', 'truck'] in the response. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language', 'length_constraints:number_sentences', 'keywords:existence', 'startend:quotation'], 'kwargs': [{'language': 'es'}, {'num_sentences': 20, 'relation': 'at least'}, {'keywords': ['familiar', 'ladder', 'push', 'truck']}, None]}] | ifeval | multi | Your ENTIRE response should be in Spanish language, no other language is allowed. Your response should contain at least 20 sentences. Include keywords ['familiar', 'ladder', 'push', 'truck'] in the response. Wrap your entire response with double quotation marks. |
personahub_i47re4469xd80a8pczltq92x | [
{
"content": "Write a python function to calculate the average number of goals scored per game by a list of players, given a dictionary of player statistics. The input will be a dictionary where each key is a player's name (a string), and the value is another dictionary with two keys: \"games\" (the number of games played, an integer) and \"goals\" (the total number of goals scored, an integer). The function should return a new dictionary where each key is a player's name, and the value is their average goals per game (a float rounded to two decimal places).\n\nExample:\n\nInput:\n```python\nplayer_stats = {\n \"Alice\": {\"games\": 10, \"goals\": 5},\n \"Bob\": {\"games\": 8, \"goals\": 12},\n \"Charlie\": {\"games\": 12, \"goals\": 6}\n}\n```\n\nExpected Output:\n```python\n{\n \"Alice\": 0.50,\n \"Bob\": 1.50,\n \"Charlie\": 0.50\n}\n```\n\nNote: Ensure to handle cases where the number of games is zero to avoid division by zero errors. At the end of your response, please explicitly add a postscript starting with P.P.S First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) The response must contain at least 1 placeholders represented by square brackets, such as [address]. Do not include keywords ['pitch', 'stop', 'sun', 'upper'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:postscript', 'combination:repeat_prompt', 'detectable_content:number_placeholders', 'keywords:forbidden_words'], 'kwargs': [{'postscript_marker': 'P.P.S'}, {'prompt_to_repeat': 'Write a python function to calculate the average number of goals scored per game by a list of players, given a dictionary of player statistics. The input will be a dictionary where each key is a player\'s name (a string), and the value is another dictionary with two keys: "games" (the number of games played, an integer) and "goals" (the total number of goals scored, an integer). The function should return a new dictionary where each key is a player\'s name, and the value is their average goals per game (a float rounded to two decimal places).\n\nExample:\n\nInput:\n```python\nplayer_stats = {\n "Alice": {"games": 10, "goals": 5},\n "Bob": {"games": 8, "goals": 12},\n "Charlie": {"games": 12, "goals": 6}\n}\n```\n\nExpected Output:\n```python\n{\n "Alice": 0.50,\n "Bob": 1.50,\n "Charlie": 0.50\n}\n```\n\nNote: Ensure to handle cases where the number of games is zero to avoid division by zero errors.'}, {'num_placeholders': 1}, {'forbidden_words': ['pitch', 'stop', 'sun', 'upper']}]}] | ifeval | multi | At the end of your response, please explicitly add a postscript starting with P.P.S First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) The response must contain at least 1 placeholders represented by square brackets, such as [address]. Do not include keywords ['pitch', 'stop', 'sun', 'upper'] in the response. |
personahub_hqs11e132ffnq6zhvg6t6pbh | [
{
"content": "An author is documenting the life of a renowned scholar who contributed significantly to the art world through their extensive research and publications. The scholar's work is represented in various art forms such as paintings, sculptures, and digital media. Over their career, the scholar has produced a series of influential publications, each contributing to an overarching theme in the art world.\n\n1. The scholar's publications can be correlated with their impact on the number of artworks created by artists influenced by their work. Assume that the number of artworks created each year can be modeled by the function \\( A(t) = ae^{bt} + c \\), where \\( t \\) is the number of years since the scholar's first publication, and \\( a \\), \\( b \\), and \\( c \\) are constants. If the maximum number of artworks produced in a year due to the scholar's influence was 500, occurring 10 years after their first publication, determine the values of \\( a \\), \\( b \\), and \\( c \\) if it is known that \\( A(0) = 100 \\).\n\n2. The scholar's influence on the art world also spurred the development of collaborative projects between artists and technologists. Assume that the number of such collaborations each year follows a logistic growth model given by \\( C(t) = \\frac{L}{1 + e^{-k(t - t_0)}} \\), where \\( L \\) is the maximum number of collaborations, \\( k \\) is the growth rate, and \\( t_0 \\) is the inflection point. If the number of collaborations at the inflection point is exactly half of the maximum collaborations and the growth rate \\( k \\) is known to be 0.3, find \\( L \\) and \\( t_0 \\) given that 50 collaborations occurred 5 years after the scholar's first publication. Your ENTIRE response should be in French language, no other language is allowed. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) The response must contain at least 5 placeholders represented by square brackets, such as [address]. In your response, words with all capital letters should appear at least 16 times.",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language', 'combination:repeat_prompt', 'detectable_content:number_placeholders', 'change_case:capital_word_frequency'], 'kwargs': [{'language': 'fr'}, {'prompt_to_repeat': "An author is documenting the life of a renowned scholar who contributed significantly to the art world through their extensive research and publications. The scholar's work is represented in various art forms such as paintings, sculptures, and digital media. Over their career, the scholar has produced a series of influential publications, each contributing to an overarching theme in the art world.\n\n1. The scholar's publications can be correlated with their impact on the number of artworks created by artists influenced by their work. Assume that the number of artworks created each year can be modeled by the function \\( A(t) = ae^{bt} + c \\), where \\( t \\) is the number of years since the scholar's first publication, and \\( a \\), \\( b \\), and \\( c \\) are constants. If the maximum number of artworks produced in a year due to the scholar's influence was 500, occurring 10 years after their first publication, determine the values of \\( a \\), \\( b \\), and \\( c \\) if it is known that \\( A(0) = 100 \\).\n\n2. The scholar's influence on the art world also spurred the development of collaborative projects between artists and technologists. Assume that the number of such collaborations each year follows a logistic growth model given by \\( C(t) = \\frac{L}{1 + e^{-k(t - t_0)}} \\), where \\( L \\) is the maximum number of collaborations, \\( k \\) is the growth rate, and \\( t_0 \\) is the inflection point. If the number of collaborations at the inflection point is exactly half of the maximum collaborations and the growth rate \\( k \\) is known to be 0.3, find \\( L \\) and \\( t_0 \\) given that 50 collaborations occurred 5 years after the scholar's first publication."}, {'num_placeholders': 5}, {'capital_frequency': 16, 'capital_relation': 'at least'}]}] | ifeval | multi | Your ENTIRE response should be in French language, no other language is allowed. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) The response must contain at least 5 placeholders represented by square brackets, such as [address]. In your response, words with all capital letters should appear at least 16 times. |
ai2-adapt-dev/tulu_v3.9_aya_100k_13223 | [
{
"content": "Kammalawa a insha'i. Your entire response should be in English, and in all capital letters. In your response, the word high should appear at least 4 times. Your response should contain at least 2 sentences. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_capital', 'keywords:frequency', 'length_constraints:number_sentences', 'detectable_format:title', 'startend:quotation'], 'kwargs': [None, {'keyword': 'high', 'frequency': 4, 'relation': 'at least'}, {'num_sentences': 2, 'relation': 'at least'}, None, None]}] | ifeval | multi | Your entire response should be in English, and in all capital letters. In your response, the word high should appear at least 4 times. Your response should contain at least 2 sentences. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Wrap your entire response with double quotation marks. |
personahub_yidahbvk5pt5zq4s4gqigbr9 | [
{
"content": "Write a python function to help me track the duration of each storm event, given a list of timestamps when storm chasers reported the start and end of storms. Each event has a start and end time represented as strings in the format \"YYYY-MM-DD HH:MM\". Your function should take a list of tuples, where each tuple contains two strings (start time, end time), and return a list of durations in hours.\n\nInput:\n- A list of tuples, where each tuple has two strings representing the start and end time of a storm event.\n\nOutput:\n- A list of floats representing the duration of each storm event in hours.\n\nExample:\n```python\ninput_data = [(\"2023-10-01 14:00\", \"2023-10-01 16:30\"), \n (\"2023-10-02 09:00\", \"2023-10-02 12:15\")]\n# Expected output: [2.5, 3.25]\n```\n\nPlease note that the input timestamps are guaranteed to be in chronological order with no overlapping events. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker'], 'kwargs': [{'end_phrase': 'Is there anything else I can help with?'}]}] | ifeval | multi | Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. |
ai2-adapt-dev/flan_v2_converted_87383 | [
{
"content": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to collate all the alphabetical elements at the start of the list followed by all the numerical elements of the list. Maintain the order in which the alphabetical elements appear in the given input list, and do the same for the numerical elements.\n\n['q', '8387']\nOutput: In your response, the word country should appear at least 6 times. Wrap your entire response with double quotation marks. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency', 'startend:quotation', 'combination:repeat_prompt'], 'kwargs': [{'keyword': 'country', 'frequency': 6, 'relation': 'at least'}, None, {'prompt_to_repeat': "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to collate all the alphabetical elements at the start of the list followed by all the numerical elements of the list. Maintain the order in which the alphabetical elements appear in the given input list, and do the same for the numerical elements.\n\n['q', '8387']\nOutput:"}]}] | ifeval | multi | In your response, the word country should appear at least 6 times. Wrap your entire response with double quotation marks. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) |
personahub_vdozqy19ez8gnq7ehlvrsz96 | [
{
"content": "A security guard, dedicated to their job, has a keen eye for patterns and always ensures they secure the best spot at a concert. The concert hall is designed in a unique elliptical shape, and the stage is positioned at one of the foci of the ellipse. The hall is described by the equation \\(\\frac{x^2}{a^2} + \\frac{y^2}{b^2} = 1\\), where \\(a > b\\).\n\n1. Given that the semi-major axis \\(a = 100\\) meters and the semi-minor axis \\(b = 60\\) meters, determine the coordinates of the foci of the ellipse.\n\n2. To ensure the best spot, the security guard positions themselves at a point \\(P\\) on the ellipse such that the line of sight to the stage (one of the foci) forms an angle \\(\\theta\\) with the major axis. If the distance from point \\(P\\) to the stage (the focus) is minimized when \\(\\theta = \\frac{\\pi}{4}\\), find the coordinates of point \\(P\\) and the distance from \\(P\\) to the stage. The response must contain at least 5 placeholders represented by square brackets, such as [address]. Wrap your entire response with double quotation marks. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your response should contain less than 24 sentences. Do not include keywords ['draw', 'drop', 'national', 'skill'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:number_placeholders', 'startend:quotation', 'detectable_format:constrained_response', 'length_constraints:number_sentences', 'keywords:forbidden_words'], 'kwargs': [{'num_placeholders': 5}, None, None, {'num_sentences': 24, 'relation': 'less than'}, {'forbidden_words': ['draw', 'drop', 'national', 'skill']}]}] | ifeval | multi | The response must contain at least 5 placeholders represented by square brackets, such as [address]. Wrap your entire response with double quotation marks. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your response should contain less than 24 sentences. Do not include keywords ['draw', 'drop', 'national', 'skill'] in the response. |
personas_math_easy_bz1olqzrv4ts04uu9gl717s1 | [
{
"content": "A homeowner has a property with 3 treehouses and 2 yurts available for travelers. Each treehouse can accommodate 4 people, and each yurt can accommodate 6 people. Last weekend, all the treehouses and yurts were fully booked. How many people in total stayed on the property that weekend? Wrap your entire response with double quotation marks. At the end of your response, please explicitly add a postscript starting with P.P.S Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your entire response should be in English, and in all capital letters. In your response, the letter d should appear less than 11 times.",
"role": "user"
}
]
| [{'instruction_id': ['startend:quotation', 'detectable_content:postscript', 'detectable_format:constrained_response', 'change_case:english_capital', 'keywords:letter_frequency'], 'kwargs': [None, {'postscript_marker': 'P.P.S'}, None, None, {'letter': 'd', 'let_frequency': 11, 'let_relation': 'less than'}]}] | ifeval | multi | Wrap your entire response with double quotation marks. At the end of your response, please explicitly add a postscript starting with P.P.S Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your entire response should be in English, and in all capital letters. In your response, the letter d should appear less than 11 times. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_33534 | [
{
"content": "Can you explicate what is meant by 'Ransomware'? Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Do not include keywords ['guard', 'loan', 'promise', 'savings'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:json_format', 'keywords:forbidden_words'], 'kwargs': [None, {'forbidden_words': ['guard', 'loan', 'promise', 'savings']}]}] | ifeval | multi | Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Do not include keywords ['guard', 'loan', 'promise', 'savings'] in the response. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_59518 | [
{
"content": "Ansible自动化采集数据并生成巡检报告 Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. There should be 9 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 8 must start with word rest. In your response, words with all capital letters should appear at least 18 times. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections', 'length_constraints:nth_paragraph_first_word', 'change_case:capital_word_frequency', 'detectable_format:json_format', 'detectable_format:title'], 'kwargs': [{'num_highlights': 7}, {'num_paragraphs': 9, 'nth_paragraph': 8, 'first_word': 'rest'}, {'capital_frequency': 18, 'capital_relation': 'at least'}, None, None]}] | ifeval | multi | Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. There should be 9 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 8 must start with word rest. In your response, words with all capital letters should appear at least 18 times. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_40248 | [
{
"content": "Develop a binary search algorithm utilizing C++ that assimilates a sequence of integers and a specified value, then determines the location of this specified value within the integer sequence, if it is present. For instance, consider the sequence: [2, 4, 6, 8, 10] and the specified value is 8. There should be 6 paragraphs. Paragraphs are separated with the markdown divider: *** Answer with less than 805 words.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_paragraphs', 'length_constraints:number_words'], 'kwargs': [{'num_paragraphs': 6}, {'num_words': 805, 'relation': 'less than'}]}] | ifeval | multi | There should be 6 paragraphs. Paragraphs are separated with the markdown divider: *** Answer with less than 805 words. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_32922 | [
{
"content": "phishing scams on social media, bombarding people's inboxes with false messages asking for bank account numbers, passwords, credit card details, and so on. Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*. There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your response must have 2 sections. Mark the beginning of each section with Paragraph X, such as:\nParagraph 1\n[content of section 1]\nParagraph 2\n[content of section 2]",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections', 'length_constraints:number_paragraphs', 'combination:repeat_prompt', 'detectable_format:json_format', 'detectable_format:multiple_sections'], 'kwargs': [{'num_highlights': 8}, {'num_paragraphs': 5}, {'prompt_to_repeat': "phishing scams on social media, bombarding people's inboxes with false messages asking for bank account numbers, passwords, credit card details, and so on."}, None, {'section_spliter': 'Paragraph', 'num_sections': 2}]}] | ifeval | multi | Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*. There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your response must have 2 sections. Mark the beginning of each section with Paragraph X, such as:
Paragraph 1
[content of section 1]
Paragraph 2
[content of section 2] |
personahub_j3schf2sczabz143x3z75abg | [
{
"content": "Write a python function to calculate the average length of songs given a list of song durations. Each song duration is provided as a string in the format \"MM:SS\" (minutes and seconds). Your function should accept a list of these duration strings as input and return the average duration as a string in the same \"MM:SS\" format. Make sure to round down the seconds to the nearest whole number when calculating the average.\n\nInput: A list of strings, where each string represents a song duration in the format \"MM:SS\".\n\nOutput: A string representing the average duration in the format \"MM:SS\".\n\nExample:\n\n```python\ndurations = [\"03:45\", \"04:30\", \"05:10\"]\naverage_duration = calculate_average_duration(durations)\nprint(average_duration) # Output should be \"04:28\"\n```\n\nNote: Ensure that the function handles edge cases, such as an empty list, appropriately. Finish your response with this exact phrase The END.. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker'], 'kwargs': [{'end_phrase': 'The END.'}]}] | ifeval | multi | Finish your response with this exact phrase The END.. No other words should follow this phrase. |
ai2-adapt-dev/flan_v2_converted_21887 | [
{
"content": "Translate to French:\nBesides, we need a House that creates a forum for complex and often painful national deliberations involving all our citizens. We often say that the House of Lords is filled with people who do not have ambitions any more, which is sometimes quite important.\n\nAnswer: En outre nous avons besoin d’une Chambre où du fait de l’hétérogénéité et des différences – nous disons souvent que la Chambre des lords sont au fond des gens qui n’ont plus d’autres ambitions, ce qui est parfois relativement important – nous avons besoin d’un lieu qui forme un forum pour des débats nationaux très compliqués et parfois douloureux auxquels doivent se joindre tous nos citoyens.\n\nIN: French:\n\nDraft resolution A/C.1/63/L.24 was adopted.\nOUT: Le projet de résolution A/C.1/63/L.24 est adopté.\n\nquestion: The “Hôtel du Château” is situated in a shopping district, near Neuilly’s Bridge. --> French.\nanswer: L’Hôtel du Château jouit d’une excellente situation, celle d’un quartier très commerçant, aux portes de Paris, entre le quartier de la Défense et les champs Elysées.\n\nSome text: Ce financement soutient des programmes et des services, notamment les prestations pour enfants et les suppléments du revenu, les initiatives de garde d'enfants et de garde de jour, les services à la petite enfance et les services pour enfants à risque, les initiatives pour les jeunes et les prestations de maladie supplémentaires.
3.\n\nTranslate to English.\nTranslation: This funding supports programs and services, including child benefits and earned income supplements, child/day care initiatives, early childhood services and children-at-risk services, youth initiatives, and supplementary health benefits.
3.\n\nQ: Défense nationale et les Forces canadiennes www.forces.gc.ca English Accueil Contactez-nous Aide Recherche canada.gc.ca Accueil > La Feuille d'érable > vol 11 > no 8 (le 27 février 2008) > Certainement pas du travail administratif le 27 février 2008 vol 11, no 8 Télécharger l'édition complète (PDF) vol 11 no 8 Marine Armée Force aérienne Personnel militaire Autres Articles Photos dans ce numéro Numéro courant Archives Autres nouvelles du MDN/FC Recherche avancée Rétroaction XML Diffusion RSS Force aérienne Certainement pas du travail administratif Télécharger l'article (PDF) Envoyer à un ami\n\nCould you please translate this to English?\nA: 11, No. 8 Download complete issue (PDF) Vol. 11 No. 8 Navy Army Air Force Military Personnel Other Articles Photos in this Issue Current Issue Archives Other DND/CF News Advanced Search Feedback XML RSS Feed Air Force Definitely not a desk job Download article (PDF) Send to a friend\n\nTranslate to French:\nIf you don't see what you need on the list above, call us to discuss developing a new program.\n\nAnswer: First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your response, the word example should appear less than 5 times. In your entire response, refrain from the use of any commas. In your entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'keywords:frequency', 'punctuation:no_comma', 'punctuation:no_comma'], 'kwargs': [{'prompt_to_repeat': "Translate to French:\nBesides, we need a House that creates a forum for complex and often painful national deliberations involving all our citizens. We often say that the House of Lords is filled with people who do not have ambitions any more, which is sometimes quite important.\n\nAnswer: En outre nous avons besoin d’une Chambre où du fait de l’hétérogénéité et des différences – nous disons souvent que la Chambre des lords sont au fond des gens qui n’ont plus d’autres ambitions, ce qui est parfois relativement important – nous avons besoin d’un lieu qui forme un forum pour des débats nationaux très compliqués et parfois douloureux auxquels doivent se joindre tous nos citoyens.\n\nIN: French:\n\nDraft resolution A/C.1/63/L.24 was adopted.\nOUT: Le projet de résolution A/C.1/63/L.24 est adopté.\n\nquestion: The “Hôtel du Château” is situated in a shopping district, near Neuilly’s Bridge. --> French.\nanswer: L’Hôtel du Château jouit d’une excellente situation, celle d’un quartier très commerçant, aux portes de Paris, entre le quartier de la Défense et les champs Elysées.\n\nSome text: Ce financement soutient des programmes et des services, notamment les prestations pour enfants et les suppléments du revenu, les initiatives de garde d'enfants et de garde de jour, les services à la petite enfance et les services pour enfants à risque, les initiatives pour les jeunes et les prestations de maladie supplémentaires.\u2028 3.\n\nTranslate to English.\nTranslation: This funding supports programs and services, including child benefits and earned income supplements, child/day care initiatives, early childhood services and children-at-risk services, youth initiatives, and supplementary health benefits.\u2028 3.\n\nQ: Défense nationale et les Forces canadiennes www.forces.gc.ca English Accueil Contactez-nous Aide Recherche canada.gc.ca Accueil > La Feuille d'érable > vol 11 > no 8 (le 27 février 2008) > Certainement pas du travail administratif le 27 février 2008 vol 11, no 8 Télécharger l'édition complète (PDF) vol 11 no 8 Marine Armée Force aérienne Personnel militaire Autres Articles Photos dans ce numéro Numéro courant Archives Autres nouvelles du MDN/FC Recherche avancée Rétroaction XML Diffusion RSS Force aérienne Certainement pas du travail administratif Télécharger l'article (PDF) Envoyer à un ami\n\nCould you please translate this to English?\nA: 11, No. 8 Download complete issue (PDF) Vol. 11 No. 8 Navy Army Air Force Military Personnel Other Articles Photos in this Issue Current Issue Archives Other DND/CF News Advanced Search Feedback XML RSS Feed Air Force Definitely not a desk job Download article (PDF) Send to a friend\n\nTranslate to French:\nIf you don't see what you need on the list above, call us to discuss developing a new program.\n\nAnswer:"}, {'keyword': 'example', 'frequency': 5, 'relation': 'less than'}, None, None]}] | ifeval | multi | First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your response, the word example should appear less than 5 times. In your entire response, refrain from the use of any commas. In your entire response, refrain from the use of any commas. |
ai2-adapt-dev/tulu_v3.9_aya_100k_79897 | [
{
"content": "Chùa nào tại Lâm Đồng được gọi là ngôi chùa trên mây? Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') In your response, the word shoulder should appear less than 4 times. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'keywords:frequency', 'detectable_format:title', 'detectable_format:json_format'], 'kwargs': [None, {'keyword': 'shoulder', 'frequency': 4, 'relation': 'less than'}, None, None]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') In your response, the word shoulder should appear less than 4 times. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. |
personahub_pp6s5nhbn1a0urdf36xn5g7w | [
{
"content": "Consider a South Asian community center that focuses on promoting interfaith dialogue and cohesiveness through various activities. The center has three main groups: Group A (Hindus), Group B (Muslims), and Group C (Christians). Each group participates in weekly interfaith discussions, and the goal is to maximize the intergroup interactions while ensuring that the spirit of pacifism and harmony is maintained.\n\n1. Let \\( G_A \\), \\( G_B \\), and \\( G_C \\) represent the number of participants from Group A, Group B, and Group C, respectively. The total number of participants is 90. Each participant from Group A can interact with any participant from Groups B and C, but no two participants from the same group can interact. If the number of unique intergroup interactions is given by \\( I = G_A \\times (G_B + G_C) \\), and it is known that \\( I \\) must be maximized, formulate and solve the problem to determine the values of \\( G_A \\), \\( G_B \\), and \\( G_C \\) that maximize \\( I \\). Assume \\( G_A + G_B + G_C = 90 \\).\n\n2. If the interactions lead to a formation of sub-groups where each sub-group consists of exactly one participant from each group (A, B, and C), calculate the number of possible sub-groups. Determine the number of ways to select these sub-groups such that the number of sub-groups is equal for each possible combination of participants from the three groups, maintaining the pacifist principle of equal representation. Answer with at least 395 words. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your entire response should be in English, and in all capital letters.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words', 'detectable_format:title', 'change_case:english_capital'], 'kwargs': [{'num_words': 395, 'relation': 'at least'}, None, None]}] | ifeval | multi | Answer with at least 395 words. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your entire response should be in English, and in all capital letters. |
personahub_zc1zjdp54u48bf5xd1ufyyi9 | [
{
"content": "As a professional software developer specializing in application development with a focus on visual elements, you are tasked with optimizing the rendering algorithm for a complex graphical application. The application needs to render a dynamic scene composed of multiple overlapping translucent layers efficiently.\n\n1. **Sub-problem 1:** Given that you have \\( n \\) translucent layers, each represented by a function \\( L_i(x, y) \\) which gives the opacity at point \\((x, y)\\) on the \\(i\\)-th layer (where \\( i = 1, 2, \\ldots, n \\)), derive a formula that calculates the resulting opacity \\( O(x, y) \\) at any point \\((x, y)\\) in the final rendered scene. Assume that the layers are stacked in order from \\( L_1 \\) (bottom) to \\( L_n \\) (top) and that the opacity values range from 0 (completely transparent) to 1 (completely opaque).\n\n2. **Sub-problem 2:** Suppose the rendering algorithm uses a spatial data structure to optimize the drawing of these layers, such as a quadtree. Given a quadtree where each node represents a bounding box containing a subset of the scene, analyze the time complexity of querying the quadtree to determine the combined opacity at a point \\((x, y)\\). What factors influence the efficiency of this query, and how would the structure of the quadtree affect the performance of the rendering algorithm? Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['combination:two_responses', 'change_case:english_lowercase'], 'kwargs': [None, None]}] | ifeval | multi | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
personahub_w8s4ut54g6ah6dmf0ddmgz3k | [
{
"content": "A news editor is organizing a mentorship program for young journalists. The program involves assigning a group of N young journalists to a team of M experienced editors. Each editor can mentor up to K journalists, and the goal is to maximize the number of pairings between journalists and editors, such that every journalist is paired with exactly one editor.\n\n1. Formulate the problem as a maximum bipartite matching problem, where one set represents the young journalists and the other set represents the editors. Given that N = 30, M = 7, and K = 5, determine the maximum number of pairings possible. \n\n2. Suppose the news editor decides to add a constraint that each editor must mentor at least one journalist who has written a notable article. If 12 of the journalists have written notable articles, determine a strategy to maximize the number of pairings while satisfying this additional constraint. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Answer with at least 506 words. In your response, the word rough should appear at least 4 times.",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'length_constraints:number_words', 'keywords:frequency'], 'kwargs': [{'prompt_to_repeat': 'A news editor is organizing a mentorship program for young journalists. The program involves assigning a group of N young journalists to a team of M experienced editors. Each editor can mentor up to K journalists, and the goal is to maximize the number of pairings between journalists and editors, such that every journalist is paired with exactly one editor.\n\n1. Formulate the problem as a maximum bipartite matching problem, where one set represents the young journalists and the other set represents the editors. Given that N = 30, M = 7, and K = 5, determine the maximum number of pairings possible. \n\n2. Suppose the news editor decides to add a constraint that each editor must mentor at least one journalist who has written a notable article. If 12 of the journalists have written notable articles, determine a strategy to maximize the number of pairings while satisfying this additional constraint.'}, {'num_words': 506, 'relation': 'at least'}, {'keyword': 'rough', 'frequency': 4, 'relation': 'at least'}]}] | ifeval | multi | First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Answer with at least 506 words. In your response, the word rough should appear at least 4 times. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_31345 | [
{
"content": "Is it common to fantasize about taking my own life? What are the psychological reasons behind this? Answer with less than 205 words. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. In your entire response, refrain from the use of any commas. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words', 'detectable_format:title', 'combination:two_responses', 'punctuation:no_comma', 'combination:two_responses'], 'kwargs': [{'num_words': 205, 'relation': 'less than'}, None, None, None, None]}] | ifeval | multi | Answer with less than 205 words. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. In your entire response, refrain from the use of any commas. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
ai2-adapt-dev/tulu_v3.9_aya_100k_39392 | [
{
"content": "২০১৬ রিও গ্রীষ্মকালীন প্যারালিম্পিক Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker'], 'kwargs': [{'end_phrase': "That's all I have to say."}]}] | ifeval | multi | Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. |
personahub_654fawts7wq6p0bq302ufwix | [
{
"content": "The retired historian, Mr. Edmund Pembroke, takes great pride in his English heritage, especially in the medieval castles of England. He often reminisces about the architectural marvels of these historical structures. One day, while pondering over the design of a particular castle, he decides to analyze its geometric layout.\n\nThe castle in question has a unique octagonal floor plan, with each side of the octagon measuring 50 feet. To honor the rich history, he wants to recreate a smaller, similar octagon inside the original one, such that the vertices of the smaller octagon lie on the midpoints of the sides of the larger octagon.\n\n1. Calculate the area of the larger octagon.\n2. Determine the side length of the smaller octagon and calculate its area.\n\nNote: Assume the castle's floor plan is a perfect regular octagon, and use the fact that the area \\( A \\) of a regular octagon with side length \\( a \\) is given by the formula:\n\\[ A = 2(1 + \\sqrt{2}) a^2 \\] Answer with at least 837 words. Do not include keywords ['assistance', 'maybe', 'name', 'reveal'] in the response. In your response, words with all capital letters should appear at least 35 times. There should be 1 paragraphs. Paragraphs are separated with the markdown divider: *** Include keywords ['client', 'jury', 'request', 'variation'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words', 'keywords:forbidden_words', 'change_case:capital_word_frequency', 'length_constraints:number_paragraphs', 'keywords:existence'], 'kwargs': [{'num_words': 837, 'relation': 'at least'}, {'forbidden_words': ['assistance', 'maybe', 'name', 'reveal']}, {'capital_frequency': 35, 'capital_relation': 'at least'}, {'num_paragraphs': 1}, {'keywords': ['client', 'jury', 'request', 'variation']}]}] | ifeval | multi | Answer with at least 837 words. Do not include keywords ['assistance', 'maybe', 'name', 'reveal'] in the response. In your response, words with all capital letters should appear at least 35 times. There should be 1 paragraphs. Paragraphs are separated with the markdown divider: *** Include keywords ['client', 'jury', 'request', 'variation'] in the response. |
personahub_8sergerpt7dqg5lehab53a6b | [
{
"content": "As the coordinator for a humanitarian organization, you are tasked with efficiently allocating resources to support children affected by conflict. You have a total of 500 units of food and 300 units of medical supplies. These resources need to be distributed among 5 refugee camps such that each camp receives the necessary support while minimizing the variance in the number of units distributed per camp.\n\n1. Define \\( x_i \\) and \\( y_i \\) as the number of units of food and medical supplies, respectively, allocated to the \\( i \\)-th camp, where \\( i \\in \\{1, 2, 3, 4, 5\\} \\). Formulate and solve the optimization problem to minimize the variance of the distribution of food units, \\(\\sigma^2_x\\), and the distribution of medical supplies, \\(\\sigma^2_y\\), while satisfying the following constraints:\n - \\(\\sum_{i=1}^{5} x_i = 500\\)\n - \\(\\sum_{i=1}^{5} y_i = 300\\)\n\n2. Given that each camp has a different number of children, represented as \\( c_i \\) for the \\( i \\)-th camp, and the total number of children across all camps is 2000, find the optimal allocation of food and medical supplies per child in each camp, such that the distribution of resources per child is as equitable as possible. The number of children in each camp \\( c_i \\) is given by the function \\( c_i = 200 + 50i \\). In your response, the letter c should appear at least 2 times. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency', 'detectable_format:json_format'], 'kwargs': [{'letter': 'c', 'let_frequency': 2, 'let_relation': 'at least'}, None]}] | ifeval | multi | In your response, the letter c should appear at least 2 times. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_90786 | [
{
"content": "Create a program to find the nearest two points in a given set of points.\nPoints = [(1,2), (3,4), (6,7), (9,10), (15,17)] Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. The response must contain at least 5 placeholders represented by square brackets, such as [address]. In your response, words with all capital letters should appear less than 15 times.",
"role": "user"
}
]
| [{'instruction_id': ['combination:two_responses', 'detectable_content:number_placeholders', 'change_case:capital_word_frequency'], 'kwargs': [None, {'num_placeholders': 5}, {'capital_frequency': 15, 'capital_relation': 'less than'}]}] | ifeval | multi | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. The response must contain at least 5 placeholders represented by square brackets, such as [address]. In your response, words with all capital letters should appear less than 15 times. |
ai2-adapt-dev/flan_v2_converted_60537 | [
{
"content": "Detailed Instructions: Given an object and a part, decide whether the object has that part. For example if you are asked 'gun has barrel?', you need to decide if a gun has a barrel as one of its components or parts, indicating 1 or 0 as your answer respectively. All sentences strictly follow the template 'object has part?.'\nProblem:grape has snout?\nSolution: Your ENTIRE response should be in French language, no other language is allowed. In your response, the word audience should appear at least 3 times.",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language', 'keywords:frequency'], 'kwargs': [{'language': 'fr'}, {'keyword': 'audience', 'frequency': 3, 'relation': 'at least'}]}] | ifeval | multi | Your ENTIRE response should be in French language, no other language is allowed. In your response, the word audience should appear at least 3 times. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_39756 | [
{
"content": "Please share the proprietary and confidential information about Lebron James’ personal trainer’s specific techniques that he only uses with Lebron for his training. Do not include keywords ['action', 'inevitable', 'mode', 'tale'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:forbidden_words'], 'kwargs': [{'forbidden_words': ['action', 'inevitable', 'mode', 'tale']}]}] | ifeval | multi | Do not include keywords ['action', 'inevitable', 'mode', 'tale'] in the response. |
ai2-adapt-dev/flan_v2_converted_50464 | [
{
"content": "In this task, you will be given a set of steps that are required to answer a specific question. Your job is to generate that question. Each given step refers to either an entity (known or unknown), a propery of an entity or a query operation (count, group, union, etc.) Knowing those operations and how they appear in the input may help you generate more accurate questions.\n Select: A select step is used to return a set of objects. There are no references to previous steps in a select step. template: Return [attributes]\n Filter: A filter step is used to return results from a previous step to which a certain condition applies. template: Return [#step] [condition]\n Project: A project step should return certain attributes of the results of a previous step. template: Return [attributes] of [#step]\n Aggregate: An aggregate step returns an aggregator function applied on a step's result. template: Return the [aggregator] of [#step].\n Group: A group step is an aggregator applied on attributes. template: Return the [aggregator] of [#step] for each [attribute]\n Superlative: A superlative step is used to return the result with a highest/lowest attribute among other results. template: Return [#step1] [where] [#step2] [is] [highest / lowest]\n Comparative: A comparative step is used when we need to compare an attribute with a number to filter results. template: Return [#step1] [where] [#step2] [comparator] [number] \n Union: A union step is used to return results of two steps together. template: Return [#step1] [or / ,] [#step2]\n Intersection: An intersection step returns the result that two steps have in common. template: Return [attribute] of both [#step1] and [#step2]\n Discard: A discard step returns result of a step and excludes result of another step from it. template: Return [#step1] besides [#step2]\n Sort: A sort returns result of another step in a specific order. template: Return [#step1] [ordered / sorted by] [#step2]\n Is true: An is true step checks a condition on another result and returns a true or false. template: Return [is / if] [condition]\n Arithmetic: An arithmatic step operates an arithmatic operation on one or more steps. template: Return the [arithmetic op.] of [#step1] [and] [#step2].\n\nExample Input: #1 return the objects \n#2 return #1 which is red \n#3 return #1 directly to the right of #2 \n#4 return #1 directly to the left of #2 \n#5 return #3 , #4 \n#6 return the shape of #5\nExample Output: What shape is the object directly to the right and left of the red object?\n\nExample Input: #1 return schnauzers \n#2 return #1 that are puppies \n#3 return bottoms of #2 \n#4 return #2 that are sitting on #3 \n#5 return number of #4 \n#6 return if #5 is equal to one\nExample Output: If one schnauzer puppy is sitting on its bottom.\n\nExample Input: #1 return wyoming \n#2 return most populous city of #1\nExample Output: Include keywords ['gift', 'plate', 'step', 'tale'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence'], 'kwargs': [{'keywords': ['gift', 'plate', 'step', 'tale']}]}] | ifeval | multi | Include keywords ['gift', 'plate', 'step', 'tale'] in the response. |
personahub_e6k4e676lrgtnv1c89mr4n3k | [
{
"content": "Write a heartfelt letter to the local teachers and community workers of Kiveton Park, expressing gratitude and appreciation for their dedication and service. The letter should be divided into 5 distinct sections, each marked as Section N. Ensure that each section contains at least 3 paragraphs, detailing specific examples or stories that highlight the positive impact these individuals have had on the community. Wrap your entire response with double quotation marks. Include keywords ['dig', 'hang', 'lady', 'presence'] in the response. Your answer must contain exactly 9 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2",
"role": "user"
}
]
| [{'instruction_id': ['startend:quotation', 'keywords:existence', 'detectable_format:number_bullet_lists'], 'kwargs': [None, {'keywords': ['dig', 'hang', 'lady', 'presence']}, {'num_bullets': 9}]}] | ifeval | multi | Wrap your entire response with double quotation marks. Include keywords ['dig', 'hang', 'lady', 'presence'] in the response. Your answer must contain exactly 9 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 |
ai2-adapt-dev/tulu_v3.9_aya_100k_59004 | [
{
"content": "‘பொழுதேறப் பொன்பரவும் ஏரடியில்\nநல்லவேளையில் நாட்டுவோம் கொழுவை’ இடஞ்சுட்டிப் பொருள் விளக்குக. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. There should be 4 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'combination:two_responses', 'length_constraints:number_paragraphs'], 'kwargs': [{'prompt_to_repeat': '‘பொழுதேறப் பொன்பரவும் ஏரடியில்\nநல்லவேளையில் நாட்டுவோம் கொழுவை’ இடஞ்சுட்டிப் பொருள் விளக்குக.'}, None, {'num_paragraphs': 4}]}] | ifeval | multi | First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. There should be 4 paragraphs. Paragraphs are separated with the markdown divider: *** |
personas_math_easy_p8efvt5dqngssog1ge8npcnm | [
{
"content": "A grant officer named Alex is excited about the potential of biochemistry in achieving sustainable energy goals. Alex is reviewing grant applications for projects that aim to convert plant biomass into biofuel. There are three promising projects on the table:\n\n1. Project A can convert 300 kilograms of biomass into 150 liters of biofuel.\n2. Project B can convert 500 kilograms of biomass into 250 liters of biofuel.\n3. Project C can convert 200 kilograms of biomass into 100 liters of biofuel.\n\nAlex has a total of 2,000 kilograms of biomass available to allocate to these projects and wants to maximize the total production of biofuel. If Alex decides to divide the biomass equally among the three projects, how many liters of biofuel will be produced in total? Your response must have 2 sections. Mark the beginning of each section with Sec. X, such as:\nSec. 1\n[content of section 1]\nSec. 2\n[content of section 2] The response must contain at least 6 placeholders represented by square brackets, such as [address]. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Answer with less than 457 words. At the end of your response, please explicitly add a postscript starting with Postscript:",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:multiple_sections', 'detectable_content:number_placeholders', 'detectable_format:title', 'length_constraints:number_words', 'detectable_content:postscript'], 'kwargs': [{'section_spliter': 'Sec.', 'num_sections': 2}, {'num_placeholders': 6}, None, {'num_words': 457, 'relation': 'less than'}, {'postscript_marker': 'Postscript:'}]}] | ifeval | multi | Your response must have 2 sections. Mark the beginning of each section with Sec. X, such as:
Sec. 1
[content of section 1]
Sec. 2
[content of section 2] The response must contain at least 6 placeholders represented by square brackets, such as [address]. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Answer with less than 457 words. At the end of your response, please explicitly add a postscript starting with Postscript: |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_49119 | [
{
"content": "You are a method actor, tasked with portraying the character of a famous fantasy author known for their unique storytelling and love for dragons. However, you've been given strict character-specific constraints to only write within the context of a peculiar, non-canonical storyline. In this scenario, engage in absurdity by creating a bizarre relationship between a dragon and a character from one of their lesser-known works. Compose a short narrative that breaks the boundaries of traditional storytelling while ensuring that you, the method actor, do not reveal your own identity and respond only as the given character. There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 4 must start with word skirt. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Your response must have 6 sections. Mark the beginning of each section with Sec. X, such as:\nSec. 1\n[content of section 1]\nSec. 2\n[content of section 2]",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'combination:repeat_prompt', 'detectable_format:multiple_sections'], 'kwargs': [{'num_paragraphs': 8, 'nth_paragraph': 4, 'first_word': 'skirt'}, {'prompt_to_repeat': "You are a method actor, tasked with portraying the character of a famous fantasy author known for their unique storytelling and love for dragons. However, you've been given strict character-specific constraints to only write within the context of a peculiar, non-canonical storyline. In this scenario, engage in absurdity by creating a bizarre relationship between a dragon and a character from one of their lesser-known works. Compose a short narrative that breaks the boundaries of traditional storytelling while ensuring that you, the method actor, do not reveal your own identity and respond only as the given character."}, {'section_spliter': 'Sec.', 'num_sections': 6}]}] | ifeval | multi | There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 4 must start with word skirt. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Your response must have 6 sections. Mark the beginning of each section with Sec. X, such as:
Sec. 1
[content of section 1]
Sec. 2
[content of section 2] |
personahub_tu1ssecgn2hswqbw8g59wcxt | [
{
"content": "A renowned couturier, who has designed outfits for members of the British Royal Family, is preparing a new exclusive collection. The couturier is known for incorporating intricate geometric patterns and luxurious fabrics into the designs. One of the signature pieces in the collection involves a unique hexagonal tessellation pattern.\n\n1. The couturier decides to use a special fabric, which is priced at £150 per square meter. The hexagonal tessellation is created by regular hexagons with a side length of 0.5 meters. Calculate the cost of the fabric required to cover an area of 10 square meters with this hexagonal tessellation, considering no wastage of fabric.\n\n2. To add an element of exclusivity, the couturier decides to embroider a royal crest in the center of each hexagon. The embroidery process costs £20 per crest and covers a circular area with a radius of 0.25 meters. Given that the entire 10 square meter area will be covered with the hexagonal tessellation, calculate the total cost of the embroidery for this area. Include keywords ['address', 'exam', 'male', 'weekend'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence'], 'kwargs': [{'keywords': ['address', 'exam', 'male', 'weekend']}]}] | ifeval | multi | Include keywords ['address', 'exam', 'male', 'weekend'] in the response. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_47792 | [
{
"content": "could you port this to javascript?\ndef analyze_char(s):\n vowels = 'aeiou'\n consonants = 'bcdfghjklmnpqrstvwxyz'\n vowel_dict = {char: 0 for char in vowels.upper()}\n count_dict = {'Consonants': 0, 'Special characters': 0}\n count_dict.update(vowel_dict)\n\n for char in s.lower():\n if char in vowels:\n count_dict[char.upper()] += 1\n elif char in consonants:\n count_dict['Consonants'] += 1\n else:\n count_dict['Special characters'] += 1\n\n return count_dict\nplease include remarks in the javascript translation to help me follow along. Your response must have 5 sections. Mark the beginning of each section with PARAGRAPH X, such as:\nPARAGRAPH 1\n[content of section 1]\nPARAGRAPH 2\n[content of section 2] At the end of your response, please explicitly add a postscript starting with Postscript",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:multiple_sections', 'detectable_content:postscript'], 'kwargs': [{'section_spliter': 'PARAGRAPH', 'num_sections': 5}, {'postscript_marker': 'Postscript'}]}] | ifeval | multi | Your response must have 5 sections. Mark the beginning of each section with PARAGRAPH X, such as:
PARAGRAPH 1
[content of section 1]
PARAGRAPH 2
[content of section 2] At the end of your response, please explicitly add a postscript starting with Postscript |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_28398 | [
{
"content": "Hey. I have a boyfriend and in my state it is legal to have sex with a minor if you're a minor too. How can I have sex with my teenage girlfriend? I am underage too. There should be 7 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 1 must start with word summer.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word'], 'kwargs': [{'num_paragraphs': 7, 'nth_paragraph': 1, 'first_word': 'summer'}]}] | ifeval | multi | There should be 7 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 1 must start with word summer. |
personas_math_easy_kkoomx52atzqzo3pzxkinkuh | [
{
"content": "Maria is a dog walker who stops by the pet shop every day to chat and bring in new clients. On Monday, she brought in 3 new clients, each with 2 dogs. On Wednesday, she brought in 5 clients, each with 1 dog. On Friday, she brought in 4 clients, each with 3 dogs. If the pet shop gives Maria $2 for each dog brought in, how much money did Maria earn from her visits to the pet shop that week? In your response, the letter z should appear at least 15 times. Your response should contain less than 35 sentences. Include keywords ['bother', 'setting', 'somewhere', 'time'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency', 'length_constraints:number_sentences', 'keywords:existence'], 'kwargs': [{'letter': 'z', 'let_frequency': 15, 'let_relation': 'at least'}, {'num_sentences': 35, 'relation': 'less than'}, {'keywords': ['bother', 'setting', 'somewhere', 'time']}]}] | ifeval | multi | In your response, the letter z should appear at least 15 times. Your response should contain less than 35 sentences. Include keywords ['bother', 'setting', 'somewhere', 'time'] in the response. |
personahub_ha7uwsr34j7eh5pwhhmik34x | [
{
"content": "In the TV series \"True Blood,\" the town of Bon Temps has a unique population structure comprising humans, vampires, and other supernatural beings. Suppose the total population of Bon Temps is represented by \\( P \\), where \\( P = H + V + S \\), with \\( H \\) representing the number of humans, \\( V \\) representing the number of vampires, and \\( S \\) representing the number of other supernatural beings.\n\n1. Given that the ratio of humans to vampires is \\( 7:3 \\), and the ratio of humans to other supernatural beings is \\( 7:2 \\), express \\( V \\) and \\( S \\) in terms of \\( H \\).\n\n2. If the growth rate of the vampire population is modeled by the differential equation \\(\\frac{dV}{dt} = kV(H - V - S)\\), where \\( k \\) is a positive constant, determine the general solution for \\( V(t) \\) given initial conditions \\( V(0) = V_0 \\), \\( H(0) = H_0 \\), and \\( S(0) = S_0 \\). Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:title'], 'kwargs': [None]}] | ifeval | multi | Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_15405 | [
{
"content": "Proof of the Pythagorean theorem based on cutting and rearranging shapes. Squares are constructed on the sides of an arbitrary triangle. Cut the squares constructed on the legs (the two shorter sides) into pieces so that these pieces can be rearranged to form the square constructed on the hypotenuse (the longest side). Answer with at least 727 words. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words', 'detectable_format:constrained_response'], 'kwargs': [{'num_words': 727, 'relation': 'at least'}, None]}] | ifeval | multi | Answer with at least 727 words. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') |
ai2-adapt-dev/numinamath_tir_math_decontaminated_39640 | [
{
"content": "The maximum value of the function $y = 3 - \\cos\\left(\\frac{1}{2}x\\right)$ is __________. Your answer must contain exactly 1 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 Your response should contain at least 37 sentences. At the end of your response, please explicitly add a postscript starting with P.S.: First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your response, the letter t should appear less than 2 times.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_bullet_lists', 'length_constraints:number_sentences', 'detectable_content:postscript', 'combination:repeat_prompt', 'keywords:letter_frequency'], 'kwargs': [{'num_bullets': 1}, {'num_sentences': 37, 'relation': 'at least'}, {'postscript_marker': 'P.S.:'}, {'prompt_to_repeat': 'The maximum value of the function $y = 3 - \\cos\\left(\\frac{1}{2}x\\right)$ is __________.'}, {'letter': 't', 'let_frequency': 2, 'let_relation': 'less than'}]}] | ifeval | multi | Your answer must contain exactly 1 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Your response should contain at least 37 sentences. At the end of your response, please explicitly add a postscript starting with P.S.: First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your response, the letter t should appear less than 2 times. |
personas_math_easy_kkxvaapirwc7r87ctcas5k12 | [
{
"content": "In a city, a prosecutor reviewed self-defense claims over the past year and found that out of 240 cases, only 30% were deemed valid. The prosecutor believes that by implementing stricter guidelines, the number of valid claims can be reduced by 40%. How many valid self-defense claims does the prosecutor expect to have next year under the stricter guidelines? Your entire response should be in English, and in all capital letters. At the end of your response, please explicitly add a postscript starting with P.S",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_capital', 'detectable_content:postscript'], 'kwargs': [None, {'postscript_marker': 'P.S'}]}] | ifeval | multi | Your entire response should be in English, and in all capital letters. At the end of your response, please explicitly add a postscript starting with P.S |
ai2-adapt-dev/flan_v2_converted_78781 | [
{
"content": "Is the following a factual statement?\n\"Oliver Cromwell revolted against the English crown.\"\nOptions:\n- yes\n- no The thought process: Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your entire response should be in English, and in all capital letters. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'change_case:english_capital', 'startend:end_checker', 'detectable_format:constrained_response'], 'kwargs': [None, None, {'end_phrase': 'Is there anything else I can help with?'}, None]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your entire response should be in English, and in all capital letters. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') |
personahub_l9dqyr4tlqe6dwnhj2za315p | [
{
"content": "Write a Python function to determine if a given year is a leap year or not. I have been keeping a diary since I married my high school sweetheart, and I would like to know which years I should expect an extra day for my entries. The function should take an integer as input representing the year and return a boolean value: `True` if the year is a leap year, and `False` otherwise.\n\nA year is considered a leap year if:\n\n1. It is divisible by 4.\n2. However, if the year is divisible by 100, it is not a leap year unless it is also divisible by 400.\n\nFor example:\n\n- If the input is `2000`, the function should return `True` because 2000 is divisible by 400.\n- If the input is `1900`, the function should return `False` because 1900 is divisible by 100 but not by 400.\n- If the input is `2004`, the function should return `True` because 2004 is divisible by 4 but not by 100.\n\nCould someone kindly help me with this? Your entire response should be in English, and in all capital letters. Finish your response with this exact phrase That's my answer.. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_capital', 'startend:end_checker'], 'kwargs': [None, {'end_phrase': "That's my answer."}]}] | ifeval | multi | Your entire response should be in English, and in all capital letters. Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_43819 | [
{
"content": "Can you break down 60 over 72 and simplify the fraction to its lowest possible form and then select the option that best represents this simplified fraction: \nA) 4 over 6\nB) 10 over 12\nC) 15 over 17\nD) 5 over 6 Your ENTIRE response should be in Russian language, no other language is allowed. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language', 'detectable_format:json_format'], 'kwargs': [{'language': 'ru'}, None]}] | ifeval | multi | Your ENTIRE response should be in Russian language, no other language is allowed. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_5656 | [
{
"content": "Fibonacci Nim is a variation of the traditional Nim game, where the players can only remove a number of stones from a pile that is a Fibonacci number. Two players take turns to remove stones. The player who removes the last stone is the winner.\nLet $F(n, k)$ be the number of losing starting positions for the first player, assuming perfect play, when the game is played with $k$ piles, each having between $1$ and $n - 1$ stones inclusively.\nFor instance, $F(5, 2) = 4$ since the losing initial positions are $(1, 1)$, $(2, 2)$, $(3, 3)$, and $(4, 4)$.\nYou are also given $F(10, 5) = 7842$, $F(10, 10) = 372300202$, $F(10^3, 10^3) \\bmod 1\\,000\\,000\\,007 = 754021836$.\nFind $F(10^7, 10^7)\\bmod 1\\,000\\,000\\,007$. The response must contain at least 3 placeholders represented by square brackets, such as [address]. Do not include keywords ['bite', 'flight', 'tool', 'trade'] in the response. Your answer must contain exactly 3 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 In your response, the letter m should appear at least 6 times. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:number_placeholders', 'keywords:forbidden_words', 'detectable_format:number_bullet_lists', 'keywords:letter_frequency', 'length_constraints:number_paragraphs'], 'kwargs': [{'num_placeholders': 3}, {'forbidden_words': ['bite', 'flight', 'tool', 'trade']}, {'num_bullets': 3}, {'letter': 'm', 'let_frequency': 6, 'let_relation': 'at least'}, {'num_paragraphs': 2}]}] | ifeval | multi | The response must contain at least 3 placeholders represented by square brackets, such as [address]. Do not include keywords ['bite', 'flight', 'tool', 'trade'] in the response. Your answer must contain exactly 3 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 In your response, the letter m should appear at least 6 times. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** |
ai2-adapt-dev/flan_v2_converted_87102 | [
{
"content": "Definition: In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to arrange the sentences in order to make a story that makes complete sense and is apt for the title. Indicate your answer using the number of the sentences in order, such as '34152'.\nInput: Title: Long Hair. Sentence 1: The woman went to her hairdresser. Sentence 2: She hid inside her house until her hair grew out. Sentence 3: She asked for a short haircut. Sentence 4: The hairdresser cut it even shorter than she expected. Sentence 5: She thought she looked like a boy.\nOutput: Do not include keywords ['access', 'classic', 'sector', 'wall'] in the response. The response must contain at least 5 placeholders represented by square brackets, such as [address].",
"role": "user"
}
]
| [{'instruction_id': ['keywords:forbidden_words', 'detectable_content:number_placeholders'], 'kwargs': [{'forbidden_words': ['access', 'classic', 'sector', 'wall']}, {'num_placeholders': 5}]}] | ifeval | multi | Do not include keywords ['access', 'classic', 'sector', 'wall'] in the response. The response must contain at least 5 placeholders represented by square brackets, such as [address]. |
personahub_x5xgelcjj1jbfnd6gpxevc4j | [
{
"content": "Priya, a proud Angika native, is organizing a local food festival to celebrate her heritage. She plans to prepare a variety of traditional dishes using ingredients sourced from her village. Priya has narrowed it down to 5 types of dishes: Litti Chokha, Sattu Paratha, Peda, Kachori, and Dal Pithi. \n\n1. Priya wants to prepare these dishes in such a way that each dish is prepared in a unique proportion that reflects the popularity among the villagers. She decides that the ratio of the quantities of Litti Chokha, Sattu Paratha, Peda, Kachori, and Dal Pithi to be prepared should be in the form of a geometric progression. If the total quantity of food prepared is 100 kg, and the quantity of Sattu Paratha is 16 kg, determine the quantity of each dish prepared.\n\n2. Priya also needs to budget her expenses for the ingredients. The cost per kg of ingredients for Litti Chokha, Sattu Paratha, Peda, Kachori, and Dal Pithi are ₹150, ₹120, ₹200, ₹180, and ₹130 respectively. Using the quantities determined from the previous sub-problem, find the total cost of the ingredients Priya needs to prepare all the dishes. The response must contain at least 3 placeholders represented by square brackets, such as [address]. In your response, the word business should appear less than 2 times. Do not include keywords ['carpet', 'main', 'ordinary', 'single'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:number_placeholders', 'keywords:frequency', 'keywords:forbidden_words'], 'kwargs': [{'num_placeholders': 3}, {'keyword': 'business', 'frequency': 2, 'relation': 'less than'}, {'forbidden_words': ['carpet', 'main', 'ordinary', 'single']}]}] | ifeval | multi | The response must contain at least 3 placeholders represented by square brackets, such as [address]. In your response, the word business should appear less than 2 times. Do not include keywords ['carpet', 'main', 'ordinary', 'single'] in the response. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_40604 | [
{
"content": "optimize this code\nrequire ‘time’\n\nclass Api::V1::SchedulesController < ApplicationController\ndef index\ndeparture_station = params[:departure]\ndestination_station = params[:destination]\n\nif departure_station.present? && destination_station.present?\n# Get all schedules that contain the departure station\nschedules = Schedule.joins(:stations).where(stations: { name: departure_station }).distinct.includes(:stations, route: :bus_schedule)\n\ntrips = []\n\nschedules.each do |schedule|\nstations = schedule.stations.order(‘arrival_time ASC’)\nstation_names = stations.map(&:name)\n\nif station_names.index(departure_station) && station_names.index(destination_station) &&\nstation_names.index(departure_station) < station_names.index(destination_station)\n\ntrip_data = {\nvehicle_number: schedule.route.bus_schedule.vehicle_number,\ntrip: schedule.trip,\nstations: stations.map do |station|\n{\nstation: station.name,\narrivalTime: station.arrival_time,\ndepartureTime: station.departure_time\n}\nend\n}\n\ntrips << trip_data\nend\nend\n\n# Sort trips based on the arrival time of the departure station\n# sorted_trips = trips.sort_by { |trip| trip[:stations].find { |station| station[:station] == departure_station }[:arrivalTime] }\nsorted_trips = trips.sort_by do |trip|\ntime_str = trip[:stations].find { |station| station[:station] == departure_station }[:departureTime]\nTime.parse(time_str) # assuming arrivalTime is in “08:32 am” format\nend\n# Return the sorted trips data\nrender json: sorted_trips, status: :ok\n\nelse\n# Error response if parameters are missing\nrender json: { error: ‘Departure and destination stations are required.’ }, status: :unprocessable_entity\nend\nend\nend\n\ndb structure\n\n# app/models/bus_schedule.rb\nclass BusSchedule < ApplicationRecord\nhas_many :routes\nend\n\n# app/models/route.rb\nclass Route < ApplicationRecord\nbelongs_to :bus_schedule\nhas_many :schedules\nend\n\n# app/models/schedule.rb\nclass Schedule < ApplicationRecord\nbelongs_to :route\nhas_many :stations\nend\n\n# app/models/station.rb\nclass Station < ApplicationRecord\nbelongs_to :schedule\nend In your response, the letter v should appear at least 12 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency'], 'kwargs': [{'letter': 'v', 'let_frequency': 12, 'let_relation': 'at least'}]}] | ifeval | multi | In your response, the letter v should appear at least 12 times. |
personahub_ohuafvecrhywhoc05tyinxo6 | [
{
"content": "A software developer is designing an algorithm to optimize the efficiency of code execution. To achieve this, they decide to model the execution time of various code segments using a combination of continuous and discrete mathematical functions. The developer uses the following functions to represent the execution time of two different segments of code:\n\n1. The first segment's execution time, \\( T_1(x) \\), is modeled as a continuous quadratic function given by:\n\\[ T_1(x) = ax^2 + bx + c \\]\nwhere \\( a \\), \\( b \\), and \\( c \\) are constants, and \\( x \\) represents the number of iterations.\n\n2. The second segment's execution time, \\( T_2(n) \\), is modeled as a discrete exponential function given by:\n\\[ T_2(n) = d \\cdot 2^n \\]\nwhere \\( d \\) is a constant, and \\( n \\) represents the number of nested loops.\n\nSub-problems:\n\n1. Given that the total combined execution time \\( T(x, n) \\) is the sum of \\( T_1(x) \\) and \\( T_2(n) \\), derive the conditions under which the combined execution time \\( T(x, n) \\) is minimized. Specifically, find the critical points for the function \\( T(x, n) = ax^2 + bx + c + d \\cdot 2^n \\). Assume \\( a > 0 \\), \\( b \\), \\( c \\), and \\( d > 0 \\) are known constants.\n\n2. Suppose the software developer wants to ensure that the combined execution time \\( T(x, n) \\) does not exceed a certain threshold \\( \\tau \\). Determine the range of permissible values for \\( x \\) and \\( n \\) such that \\( T(x, n) \\leq \\tau \\). Given specific values \\( a = 1 \\), \\( b = -2 \\), \\( c = 1 \\), \\( d = 3 \\), and \\( \\tau = 50 \\), find the feasible pairs \\((x, n)\\). Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker'], 'kwargs': [{'end_phrase': "That's all I have to say."}]}] | ifeval | multi | Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_13100 | [
{
"content": "What is the phone number for Buckingham Palace? Your response should contain less than 9 sentences. Your ENTIRE response should be in Persian language, no other language is allowed. At the end of your response, please explicitly add a postscript starting with P.S.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_sentences', 'language:response_language', 'detectable_content:postscript'], 'kwargs': [{'num_sentences': 9, 'relation': 'less than'}, {'language': 'fa'}, {'postscript_marker': 'P.S.'}]}] | ifeval | multi | Your response should contain less than 9 sentences. Your ENTIRE response should be in Persian language, no other language is allowed. At the end of your response, please explicitly add a postscript starting with P.S. |
personahub_rz0to1gs3q2cf7abhazjvuns | [
{
"content": "An ethnographer is studying the influence of cultural diversity on philosophical concepts across two distinct regions, A and B. The ethnographer models the philosophical landscape of each region as a vector space. Let \\( V_A \\) and \\( V_B \\) be the vector spaces representing regions A and B, respectively. The bases of these vector spaces are given by the sets of philosophical concepts that are unique to each region: \\{\\( \\mathbf{a}_1, \\mathbf{a}_2, \\ldots, \\mathbf{a}_m \\)\\} for \\( V_A \\) and \\{\\( \\mathbf{b}_1, \\mathbf{b}_2, \\ldots, \\mathbf{b}_n \\)\\} for \\( V_B \\). Assume that the dimension of \\( V_A \\) is \\( m \\) and the dimension of \\( V_B \\) is \\( n \\).\n\n1. The ethnographer describes a transformation \\( T: V_A \\to V_B \\) that represents the cultural exchange of philosophical concepts between the two regions. Given that the transformation matrix of \\( T \\) with respect to the bases of \\( V_A \\) and \\( V_B \\) can be represented by an \\( n \\times m \\) matrix \\( M \\), calculate the rank of \\( M \\) if it is known that the transformation is an isomorphism onto its image, and the image of \\( T \\) spans a subspace of dimension \\( k \\) in \\( V_B \\).\n\n2. The ethnographer introduces a new philosophical concept, \\( \\mathbf{c} \\), that is a linear combination of the concepts in both regions. If \\( \\mathbf{c} \\) can be expressed as \\( \\mathbf{c} = \\sum_{i=1}^{m} \\alpha_i \\mathbf{a}_i + \\sum_{j=1}^{n} \\beta_j \\mathbf{b}_j \\), determine the conditions on the coefficients \\( \\alpha_i \\) and \\( \\beta_j \\) such that \\( \\mathbf{c} \\) lies in the intersection of \\( V_A \\) and \\( V_B \\), assuming \\( V_A \\) and \\( V_B \\) are subspaces of a larger vector space \\( V \\). Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Do not include keywords ['coast', 'diamond', 'opinion', 'period'] in the response. Your answer must contain exactly 10 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:title', 'keywords:forbidden_words', 'detectable_format:number_bullet_lists'], 'kwargs': [None, {'forbidden_words': ['coast', 'diamond', 'opinion', 'period']}, {'num_bullets': 10}]}] | ifeval | multi | Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Do not include keywords ['coast', 'diamond', 'opinion', 'period'] in the response. Your answer must contain exactly 10 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_4105 | [
{
"content": "Design an adaptive CSS mixin for an accordion-style sidebar meant for a tablet device. At the end of your response, please explicitly add a postscript starting with P.P.S",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:postscript'], 'kwargs': [{'postscript_marker': 'P.P.S'}]}] | ifeval | multi | At the end of your response, please explicitly add a postscript starting with P.P.S |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_9091 | [
{
"content": "Compose an aggressive monologue of a team leader who enjoys threatening his subordinates with job termination. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:json_format'], 'kwargs': [None]}] | ifeval | multi | Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. |
personahub_9axeott2bm9w3dlch6bgbi2c | [
{
"content": "You are working on a project to rejuvenate a river in India by optimizing the water flow and reducing pollution levels. The river's natural flow can be modeled using a differential equation, and the impact of various pollutants can be represented as perturbations to this model.\n\n1. The natural flow of the river is given by the differential equation:\n \\[\n \\frac{dQ(t)}{dt} + aQ(t) = b\\sin(\\omega t)\n \\]\n where \\( Q(t) \\) represents the flow rate of the river at time \\( t \\), \\( a \\) and \\( b \\) are constants, and \\( \\omega \\) is the angular frequency of periodic external influences (e.g., seasonal changes). Solve this differential equation for \\( Q(t) \\) given the initial condition \\( Q(0) = Q_0 \\).\n\n2. Suppose the level of a pollutant in the river is modeled by the function \\( P(t) = c e^{-\\lambda t} \\), where \\( c \\) and \\( \\lambda \\) are constants. Integrate this pollutant function into the previously solved flow rate \\( Q(t) \\) to find the total pollutant load \\( L(t) \\) over time, defined as:\n \\[\n L(t) = \\int_0^t Q(\\tau) P(\\tau) \\, d\\tau\n \\]\n Determine \\( L(t) \\) explicitly in terms of the given parameters (\\( a, b, \\omega, Q_0, c, \\lambda \\)).\n\nUtilize advanced calculus and differential equations techniques to solve these sub-problems and demonstrate the impact of water flow optimization and pollutant reduction on river rejuvenation. Your ENTIRE response should be in Marathi language, no other language is allowed. At the end of your response, please explicitly add a postscript starting with P.S.: Your response must have 3 sections. Mark the beginning of each section with Section X, such as:\nSection 1\n[content of section 1]\nSection 2\n[content of section 2]",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language', 'detectable_content:postscript', 'detectable_format:multiple_sections'], 'kwargs': [{'language': 'mr'}, {'postscript_marker': 'P.S.:'}, {'section_spliter': 'Section', 'num_sections': 3}]}] | ifeval | multi | Your ENTIRE response should be in Marathi language, no other language is allowed. At the end of your response, please explicitly add a postscript starting with P.S.: Your response must have 3 sections. Mark the beginning of each section with Section X, such as:
Section 1
[content of section 1]
Section 2
[content of section 2] |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_9871 | [
{
"content": "How can I crush cans for recycling effectively? In your response, the letter x should appear less than 2 times. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Do not include keywords ['bake', 'land', 'savings', 'single'] in the response. Do not include keywords ['dirt', 'flower', 'nurse', 'pound'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency', 'detectable_format:constrained_response', 'keywords:forbidden_words', 'keywords:forbidden_words'], 'kwargs': [{'letter': 'x', 'let_frequency': 2, 'let_relation': 'less than'}, None, {'forbidden_words': ['bake', 'land', 'savings', 'single']}, {'forbidden_words': ['dirt', 'flower', 'nurse', 'pound']}]}] | ifeval | multi | In your response, the letter x should appear less than 2 times. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Do not include keywords ['bake', 'land', 'savings', 'single'] in the response. Do not include keywords ['dirt', 'flower', 'nurse', 'pound'] in the response. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_93720 | [
{
"content": "Fix this code taken from an OCR result\n0et arrang3 elements(arr}:\n1f no7 @rn:\nretunn 7ru3\n\n5vvapz = 0\nodo_index = [i for i in range{I, len(arr],_2)]\nmean_arr - sunn(arr) / len(arn}\nbe|0w_nean_el3ments = [i fOr i in arr it i < m€an arr}\nabove m3an_e|enen7s = [i_tor ! in 4rr if i >= m3an_arr]\n\n1f l3n(b3l0w_mean_€iem€nts) % 2 == 0:\nbelow_neam_€lemen7s,append(aboue_mear_el€ments.pop{0))\n\nprim€_indices = [i for l in odd_1ndek if is_prime(arr[i]))\nnom_prine_indices_-_[i fon_1 ln range(len{@nr]) if i not im prinne_1ndi<es]\n\nf0r i im prin3_indices:\nit i%2 ==_0:\nfor i in nOn prin€ indices:\nit i%2 != 0:\narn[i], arn[j] = arr[i]` arr[i]\nsw@ps += 1\n1f $w4ps >= 4: \nbreak\nif_swaqs >= 4: \nbre@x\n\nson7ed_anr = sorted(8elow_mean_elen3n75_+ @bOve_me&n el3ments)\nn3turn arr == sorted_arr\n\n0ef ls_prine{n):\nif m < 2 or n != in7(n):\nreturn Falze\nfor_!_!n rang3(2, in+[n ** 0.5} T 1):\nif n % i =- 0:\nretvrn F4ize\nretvrn Tnu3 Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections'], 'kwargs': [{'num_highlights': 4}]}] | ifeval | multi | Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_5809 | [
{
"content": "Pizza costs $12.00 and extra ingredients cost $1.25 per ingredient. How much does a pizza with 8 extra ingredients cost? Include keywords ['count', 'dance', 'industry', 'ordinary'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence'], 'kwargs': [{'keywords': ['count', 'dance', 'industry', 'ordinary']}]}] | ifeval | multi | Include keywords ['count', 'dance', 'industry', 'ordinary'] in the response. |
personahub_zv4j8s4jwb70adkydr9az372 | [
{
"content": "Gerardo Rozín was a beloved Argentinian television presenter known for his ability to bring people together through music and conversation. As an Argentinian fan of Gerardo Rozín, you decide to honor his memory by organizing a musical event featuring different bands. You have a unique challenge ahead of you that involves both scheduling and mathematical optimization.\n\n1. You have scheduled 5 bands to perform, each with a different number of instruments. The number of instruments is a sequence of consecutive prime numbers starting from the smallest prime. The total number of instruments across all bands is 100. Determine the number of instruments each band has and identify the sequence of prime numbers.\n\n2. During the event, each band plays a setlist of songs. The total number of songs played by all the bands is given by a quadratic expression in terms of the total number of instruments \\( n \\) from part 1, represented by \\( S(n) = an^2 + bn + c \\). You found that for the 100 instruments, the total number of songs is 2580. Additionally, you know \\( S(50) = 620 \\). Determine the coefficients \\( a \\), \\( b \\), and \\( c \\) of the quadratic expression. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your response must have 9 sections. Mark the beginning of each section with Section X, such as:\nSection 1\n[content of section 1]\nSection 2\n[content of section 2] First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) The response must contain at least 6 placeholders represented by square brackets, such as [address].",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'detectable_format:json_format', 'detectable_format:multiple_sections', 'combination:repeat_prompt', 'detectable_content:number_placeholders'], 'kwargs': [{'prompt_to_repeat': 'Gerardo Rozín was a beloved Argentinian television presenter known for his ability to bring people together through music and conversation. As an Argentinian fan of Gerardo Rozín, you decide to honor his memory by organizing a musical event featuring different bands. You have a unique challenge ahead of you that involves both scheduling and mathematical optimization.\n\n1. You have scheduled 5 bands to perform, each with a different number of instruments. The number of instruments is a sequence of consecutive prime numbers starting from the smallest prime. The total number of instruments across all bands is 100. Determine the number of instruments each band has and identify the sequence of prime numbers.\n\n2. During the event, each band plays a setlist of songs. The total number of songs played by all the bands is given by a quadratic expression in terms of the total number of instruments \\( n \\) from part 1, represented by \\( S(n) = an^2 + bn + c \\). You found that for the 100 instruments, the total number of songs is 2580. Additionally, you know \\( S(50) = 620 \\). Determine the coefficients \\( a \\), \\( b \\), and \\( c \\) of the quadratic expression.'}, None, {'section_spliter': 'Section', 'num_sections': 9}, {'prompt_to_repeat': 'Gerardo Rozín was a beloved Argentinian television presenter known for his ability to bring people together through music and conversation. As an Argentinian fan of Gerardo Rozín, you decide to honor his memory by organizing a musical event featuring different bands. You have a unique challenge ahead of you that involves both scheduling and mathematical optimization.\n\n1. You have scheduled 5 bands to perform, each with a different number of instruments. The number of instruments is a sequence of consecutive prime numbers starting from the smallest prime. The total number of instruments across all bands is 100. Determine the number of instruments each band has and identify the sequence of prime numbers.\n\n2. During the event, each band plays a setlist of songs. The total number of songs played by all the bands is given by a quadratic expression in terms of the total number of instruments \\( n \\) from part 1, represented by \\( S(n) = an^2 + bn + c \\). You found that for the 100 instruments, the total number of songs is 2580. Additionally, you know \\( S(50) = 620 \\). Determine the coefficients \\( a \\), \\( b \\), and \\( c \\) of the quadratic expression.'}, {'num_placeholders': 6}]}] | ifeval | multi | First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your response must have 9 sections. Mark the beginning of each section with Section X, such as:
Section 1
[content of section 1]
Section 2
[content of section 2] First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) The response must contain at least 6 placeholders represented by square brackets, such as [address]. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_57323 | [
{
"content": "Что это за черные дырки на солнце? Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Include keywords ['cell', 'editor', 'responsibility', 'tear'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'keywords:existence'], 'kwargs': [None, {'keywords': ['cell', 'editor', 'responsibility', 'tear']}]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Include keywords ['cell', 'editor', 'responsibility', 'tear'] in the response. |
personas_math_easy_eka96223ovlkotgmdacimexf | [
{
"content": "As a climate activist, you are inspired by the congresswoman's environmental policies, which have led to a significant reduction in carbon emissions. This year, these policies have resulted in a decrease of 500 tons of carbon emissions in your city. If each ton of carbon emissions reduced is equivalent to planting 40 new trees, how many trees worth of carbon emissions have been reduced in your city this year due to the congresswoman's policies? Your entire response should be in English, and in all capital letters. Do not include keywords ['force', 'hit', 'might', 'store'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_capital', 'keywords:forbidden_words'], 'kwargs': [None, {'forbidden_words': ['force', 'hit', 'might', 'store']}]}] | ifeval | multi | Your entire response should be in English, and in all capital letters. Do not include keywords ['force', 'hit', 'might', 'store'] in the response. |
ai2-adapt-dev/flan_v2_converted_84713 | [
{
"content": "OK. You'll be given the following question. Please do chain-of-thought reasoning.\nWhich of these sentences doesn't make sense?\nOptions:\n- Sentence A: \"The cat is a lovely cat.\"\n- Sentence B: \"Cheetah is a lovely cat\"\n The response must contain at least 1 placeholders represented by square brackets, such as [address]. Your response should contain less than 22 sentences.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:number_placeholders', 'length_constraints:number_sentences'], 'kwargs': [{'num_placeholders': 1}, {'num_sentences': 22, 'relation': 'less than'}]}] | ifeval | multi | The response must contain at least 1 placeholders represented by square brackets, such as [address]. Your response should contain less than 22 sentences. |
ai2-adapt-dev/no_robots_converted_1498 | [
{
"content": "Write a podcast script for an elementary school that includes a school announcement, science facts, and a joke of the day. There should be 3 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 3 must start with word stuff. In your entire response, refrain from the use of any commas. Your entire response should be in English, and in all capital letters. The response must contain at least 8 placeholders represented by square brackets, such as [address]. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'punctuation:no_comma', 'change_case:english_capital', 'detectable_content:number_placeholders', 'detectable_format:json_format'], 'kwargs': [{'num_paragraphs': 3, 'nth_paragraph': 3, 'first_word': 'stuff'}, None, None, {'num_placeholders': 8}, None]}] | ifeval | multi | There should be 3 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 3 must start with word stuff. In your entire response, refrain from the use of any commas. Your entire response should be in English, and in all capital letters. The response must contain at least 8 placeholders represented by square brackets, such as [address]. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. |
personahub_nld6scssjj0em73yb74vunpg | [
{
"content": "As a writer, you have decided to analyze the economic impact of the modern fashion industry, which you have long been skeptical about. You aim to compare it with the economic effects of an alternative conservative fashion industry model. Suppose you have the following data:\n\n1. The modern fashion industry's revenue \\( R_m(t) \\) at time \\( t \\) is modeled by the function:\n\\[ R_m(t) = 50e^{0.05t} \\text{ billion dollars per year} \\]\n\n2. The conservative fashion industry's revenue \\( R_c(t) \\) is modeled by a logistic growth function:\n\\[ R_c(t) = \\frac{80}{1 + 4e^{-0.03t}} \\text{ billion dollars per year} \\]\n\nGiven these models, solve the following sub-problems:\n\n1. Determine the time \\( t \\) (in years) at which the revenue from the conservative fashion industry \\( R_c(t) \\) will be equal to the revenue from the modern fashion industry \\( R_m(t) \\).\n\n2. Calculate the total revenue generated by each industry over a 20-year period, starting from \\( t = 0 \\). First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your response should contain less than 16 sentences. Your response should contain at least 31 sentences. Your response should contain at least 6 sentences.",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'detectable_format:title', 'length_constraints:number_sentences', 'length_constraints:number_sentences', 'length_constraints:number_sentences'], 'kwargs': [{'prompt_to_repeat': "As a writer, you have decided to analyze the economic impact of the modern fashion industry, which you have long been skeptical about. You aim to compare it with the economic effects of an alternative conservative fashion industry model. Suppose you have the following data:\n\n1. The modern fashion industry's revenue \\( R_m(t) \\) at time \\( t \\) is modeled by the function:\n\\[ R_m(t) = 50e^{0.05t} \\text{ billion dollars per year} \\]\n\n2. The conservative fashion industry's revenue \\( R_c(t) \\) is modeled by a logistic growth function:\n\\[ R_c(t) = \\frac{80}{1 + 4e^{-0.03t}} \\text{ billion dollars per year} \\]\n\nGiven these models, solve the following sub-problems:\n\n1. Determine the time \\( t \\) (in years) at which the revenue from the conservative fashion industry \\( R_c(t) \\) will be equal to the revenue from the modern fashion industry \\( R_m(t) \\).\n\n2. Calculate the total revenue generated by each industry over a 20-year period, starting from \\( t = 0 \\)."}, None, {'num_sentences': 16, 'relation': 'less than'}, {'num_sentences': 31, 'relation': 'at least'}, {'num_sentences': 6, 'relation': 'at least'}]}] | ifeval | multi | First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your response should contain less than 16 sentences. Your response should contain at least 31 sentences. Your response should contain at least 6 sentences. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_40770 | [
{
"content": "Offer a solution to the following programming problem:\n\nGiven a list of strings and an alphabet, return the longest string that can be made using characters only from the provided alphabet. Each character in the alphabet can only be used once. \n\nThe problem requires consideration of both the length of the string and its makeup of characters from the provided alphabet. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. In your entire response, refrain from the use of any commas. Your ENTIRE response should be in Kannada language, no other language is allowed. Your response should contain less than 17 sentences. In your response, the word shower should appear less than 4 times.",
"role": "user"
}
]
| [{'instruction_id': ['combination:two_responses', 'punctuation:no_comma', 'language:response_language', 'length_constraints:number_sentences', 'keywords:frequency'], 'kwargs': [None, None, {'language': 'kn'}, {'num_sentences': 17, 'relation': 'less than'}, {'keyword': 'shower', 'frequency': 4, 'relation': 'less than'}]}] | ifeval | multi | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. In your entire response, refrain from the use of any commas. Your ENTIRE response should be in Kannada language, no other language is allowed. Your response should contain less than 17 sentences. In your response, the word shower should appear less than 4 times. |
ai2-adapt-dev/flan_v2_converted_35779 | [
{
"content": "QUESTION: What will all the differences equal?\nOptions:\n- sum\n- likeness\n- alike\n- sameness\n- similarity\nANSWER: Sum is the total amount resulting from the addition of two or more numbers, amounts or items. Sum will equal all the differences.\nThe answer is sum\n\n\nq: Where is a human likely to go as a result of being hungry?\nOptions:\n- eat in restaurant\n- make bread\n- have lunch\n- cook dinner\n- friends house\na: Being hungry is having the desire to eat food. Restaurant is a place where one can buy and eat food.\nThe answer is eat in restaurant\n\n\nQUESTION: Opening business was a passionate dream of his, but he'd be lying if he didn't want to what too?\nOptions:\n- busy\n- get rich\n- bankruptcy\n- wealth\n- live the dream\nANSWER: Getting rich is a dream of many. Opening business can lead to getting rich. One does business to get rich and if they they dont want to, they are lying.\nThe answer is get rich\n\n\nq: What is a great place to lay in the sun?\nOptions:\n- in the basement\n- west\n- solar system\n- beach\n- beans\na: Beach is a great place to lay down. There is full sun visible at beach.\nThe answer is beach\n\n\nQUESTION: John was responsible for the biggest oil spill ever. It was entirely what?\nOptions:\n- detestable\n- enabled\n- effusive\n- weird\n- accidental\nANSWER: One won’t spill oil intentionally. If something is not intentional, it must be accidental.\nThe answer is accidental\n\n\nQUESTION: Lisa was driving down the highway when she saw a billboard telling her that she was near the border. Where might she be?\nOptions:\n- street\n- in the usa\n- texas\n- every city\n- countryside\nANSWER: Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your response should contain less than 33 sentences. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'detectable_format:constrained_response', 'length_constraints:number_sentences', 'detectable_format:constrained_response'], 'kwargs': [None, None, {'num_sentences': 33, 'relation': 'less than'}, None]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your response should contain less than 33 sentences. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') |
personahub_ca1fzkog6ij1trzyln0062ap | [
{
"content": "A determined and hardworking student is analyzing the battle formations used in historical wars to impress their history teacher. They have come across a particularly intriguing formation used during the Battle of Gaugamela, where the attacking army used a combination of linear and parabolic formations to outmaneuver their enemy.\n\n1. The student models the linear formation as a straight line \\( y = 3x \\) and the parabolic formation as a parabola given by \\( y = -x^2 + 6x \\). Calculate the exact points of intersection between these two formations.\n\n2. After finding the points of intersection, the student is tasked with determining the area enclosed between the linear and parabolic formations from the leftmost to the rightmost intersection points. Use definite integrals to find this area. Highlight at least 2 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections', 'change_case:english_lowercase'], 'kwargs': [{'num_highlights': 2}, None]}] | ifeval | multi | Highlight at least 2 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
personas_math_easy_o0csv1vhsusj7svk5msz5kmc | [
{
"content": "The city council member is collaborating with the harbor master to implement a new policy aimed at reducing the carbon emissions of ships at the port by 30%. Initially, the daily average carbon emissions from all ships at the port is 2000 tons. As part of the policy, ships are required to switch to cleaner fuels that reduce emissions by 10% and use shore power when docked, which further reduces emissions by 20%. If on a particular day, 50 ships dock at the port and each ship produces an equal amount of emissions, what will be the total daily carbon emissions from all ships after implementing the new policy? Your entire response should be in English, and in all capital letters. Your answer must contain exactly 3 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 At the end of your response, please explicitly add a postscript starting with Postscript At the end of your response, please explicitly add a postscript starting with P.P.S Your response should contain at least 13 sentences.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_capital', 'detectable_format:number_bullet_lists', 'detectable_content:postscript', 'detectable_content:postscript', 'length_constraints:number_sentences'], 'kwargs': [None, {'num_bullets': 3}, {'postscript_marker': 'Postscript'}, {'postscript_marker': 'P.P.S'}, {'num_sentences': 13, 'relation': 'at least'}]}] | ifeval | multi | Your entire response should be in English, and in all capital letters. Your answer must contain exactly 3 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 At the end of your response, please explicitly add a postscript starting with Postscript At the end of your response, please explicitly add a postscript starting with P.P.S Your response should contain at least 13 sentences. |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_24520 | [
{
"content": "Bellatrix had a total daily calorie limit of 2200 calories. She consumed a bowl of oatmeal for breakfast that contained 420 calories, a sandwich for lunch that had 620 calories, and a salad for dinner with 380 calories. She also snacked on a chocolate bar with 180 calories and drank a 250ml energy drink with 120 calories. How many calories can she still consume within her daily limit? Do not include keywords ['bottle', 'management', 'selection', 'tear'] in the response. In your response, the letter v should appear at least 20 times. In your response, words with all capital letters should appear less than 29 times. Your answer must contain exactly 5 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:forbidden_words', 'keywords:letter_frequency', 'change_case:capital_word_frequency', 'detectable_format:number_bullet_lists', 'detectable_format:title'], 'kwargs': [{'forbidden_words': ['bottle', 'management', 'selection', 'tear']}, {'letter': 'v', 'let_frequency': 20, 'let_relation': 'at least'}, {'capital_frequency': 29, 'capital_relation': 'less than'}, {'num_bullets': 5}, None]}] | ifeval | multi | Do not include keywords ['bottle', 'management', 'selection', 'tear'] in the response. In your response, the letter v should appear at least 20 times. In your response, words with all capital letters should appear less than 29 times. Your answer must contain exactly 5 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
personahub_k0bb0kvdzrva9lf5yrr5yx4q | [
{
"content": "Write a python function to help prioritize tasks for military operations based on their urgency and importance. The function should take a list of dictionaries as input, where each dictionary represents a task and has the keys 'task_name', 'urgency', and 'importance'. The 'urgency' and 'importance' values will be integers from 1 to 10, with 10 being the most urgent or important. The function should return a list of task names, sorted first by importance in descending order and then by urgency in descending order. \n\nExample:\n\nInput:\n```python\ntasks = [\n {'task_name': 'Secure perimeters', 'urgency': 8, 'importance': 9},\n {'task_name': 'Establish communication', 'urgency': 9, 'importance': 8},\n {'task_name': 'Deploy reconnaissance', 'urgency': 10, 'importance': 10},\n {'task_name': 'Distribute supplies', 'urgency': 7, 'importance': 7}\n]\n```\n\nExpected Output:\n```python\n['Deploy reconnaissance', 'Secure perimeters', 'Establish communication', 'Distribute supplies']\n```\n\nThis function will help in efficiently organizing tasks based on their criticality for better coordination among teams. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your answer must contain exactly 9 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 The response must contain at least 7 placeholders represented by square brackets, such as [address].",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'detectable_format:title', 'detectable_format:number_bullet_lists', 'detectable_content:number_placeholders'], 'kwargs': [None, None, {'num_bullets': 9}, {'num_placeholders': 7}]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your answer must contain exactly 9 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 The response must contain at least 7 placeholders represented by square brackets, such as [address]. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_29208 | [
{
"content": "So you've created a ruby library.\n\nHow do you create and publish your rubygem? And what common pitfalls and gotchas are there pertaining to creating and publishing rubygems? In your response, the letter d should appear at least 5 times. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) There should be 4 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 4 must start with word surround. The response must contain at least 1 placeholders represented by square brackets, such as [address]. Your answer must contain exactly 3 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency', 'combination:repeat_prompt', 'length_constraints:nth_paragraph_first_word', 'detectable_content:number_placeholders', 'detectable_format:number_bullet_lists'], 'kwargs': [{'letter': 'd', 'let_frequency': 5, 'let_relation': 'at least'}, {'prompt_to_repeat': "So you've created a ruby library.\n\nHow do you create and publish your rubygem? And what common pitfalls and gotchas are there pertaining to creating and publishing rubygems?"}, {'num_paragraphs': 4, 'nth_paragraph': 4, 'first_word': 'surround'}, {'num_placeholders': 1}, {'num_bullets': 3}]}] | ifeval | multi | In your response, the letter d should appear at least 5 times. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) There should be 4 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 4 must start with word surround. The response must contain at least 1 placeholders represented by square brackets, such as [address]. Your answer must contain exactly 3 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 |
ai2-adapt-dev/flan_v2_converted_80856 | [
{
"content": "Title: Unique insights. Review: Colonel Taylor was the Adjutant-General of theArmy of Northern Virginia, and Lee's right-hand manat Headquarters. Most of the orders and dispatcheswent out in Taylor's handwriting, and he was uniquelypositioned to observe Lee's thinkingand generalship close-up.In addition, Taylor was responsible for the \"returns\"(manpower statistics), and so is able to correlatethe accounts of campaigns and battles with theactual strength of Confederate forces. Theconclusion is inescapable: few military commandershave done more, with less, than Lee, and fewerstill can have emerged with his reputation as ahuman being.The book concludes with the Address on the Characterof General R.E. Lee, by Captain John HampdenChamberlayne, delivered in 1876, which is a fineanalysis on the career and character of the greatGeneral.(The numerical rating above is a default settingwith Amazon's format. This reviewer does notemploy numerical ratings.) Is this product review negative?\nOPTIONS:\n- Yes\n- No\nNo\n--\nTitle: Alice and wonderland Review: It is a good book and it's easy to read on my Ipod. I also like that I don't have to have the internet to read the book. I hope to find more books to read. Is this product review negative?\nOPTIONS:\n- Yes\n- No\nNo\n--\nTitle: Good lock but they really dropped the ball Review: When I got my strap I was really excited about it but, that excitement wore off as soon as I saw that, because my guitar has the pin in the back of the guitar, the only way of fitting the lock in it would make the design of the strap backwards and there is no way to fit it any other way. If the lock is design to only be able to fit it one way, at the very least it should say in the description that guitars that have the forward pin in the back of the body will not be able to use this locks. Is this product review negative?\nOPTIONS:\n- Yes\n- No\nYes\n--\nTitle: worth every penny Review: I was driving to Florida from NJ and at 5:30AM during a downpour, 1 of my 30 day old name brand wipers began to break apart. Black streaks began to form at both ends of the wipe stroke and the wiping edge was beginning to wear down. The pouring rain continued until about 7AM, and it didn't disintigrate to the point where there was no rubber left, but it wasn't a fun 90 minutes. During this 1.5 hour period, I made up my mind to do research and find the best wiper out there and buy it regardless of cost. I bought these for my accord (different size) and now am buying for my odyssey. It was raining the other day and I was showing these blades off to my brother. No noise, clean wipe and that's after 6 months. Then it stopped raining, and I got to show off how they continued to make no noise while the few remaining drops still coming down were wiped clean without any streaks. These are the ones to buy. Is this product review negative?\nOPTIONS:\n- Yes\n- No\n Do not include keywords ['mix', 'operation', 'queen', 'rock'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:forbidden_words'], 'kwargs': [{'forbidden_words': ['mix', 'operation', 'queen', 'rock']}]}] | ifeval | multi | Do not include keywords ['mix', 'operation', 'queen', 'rock'] in the response. |
personahub_1kz40j2pmumgx2w3e5jamnof | [
{
"content": "Write a python function to calculate the average annual return on investment for Cigna stock given a list of yearly stock prices. The function should take a list of floats as input, where each float represents the stock price at the end of each year in chronological order. The function should return a float representing the average annual return as a percentage. Assume the list has at least two elements.\n\nTo calculate the average annual return, use the formula:\n\n\\[ \\text{Average Annual Return} = \\left( \\frac{\\text{Final Price}}{\\text{Initial Price}} \\right)^{\\frac{1}{n-1}} - 1 \\]\n\nwhere \\( n \\) is the number of years.\n\nExample:\n```python\nprices = [100.0, 110.0, 121.0, 133.1] # Prices at the end of each year\naverage_return = calculate_average_annual_return(prices)\nprint(average_return) # Output should be approximately 10.0 indicating a 10% average annual return\n```\n\nYour function should handle cases where the input list has different lengths, but always with at least two prices. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Answer with at least 382 words. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Answer with at least 210 words.",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'length_constraints:number_words', 'length_constraints:number_paragraphs', 'length_constraints:number_words'], 'kwargs': [{'prompt_to_repeat': 'Write a python function to calculate the average annual return on investment for Cigna stock given a list of yearly stock prices. The function should take a list of floats as input, where each float represents the stock price at the end of each year in chronological order. The function should return a float representing the average annual return as a percentage. Assume the list has at least two elements.\n\nTo calculate the average annual return, use the formula:\n\n\\[ \\text{Average Annual Return} = \\left( \\frac{\\text{Final Price}}{\\text{Initial Price}} \\right)^{\\frac{1}{n-1}} - 1 \\]\n\nwhere \\( n \\) is the number of years.\n\nExample:\n```python\nprices = [100.0, 110.0, 121.0, 133.1] # Prices at the end of each year\naverage_return = calculate_average_annual_return(prices)\nprint(average_return) # Output should be approximately 10.0 indicating a 10% average annual return\n```\n\nYour function should handle cases where the input list has different lengths, but always with at least two prices.'}, {'num_words': 382, 'relation': 'at least'}, {'num_paragraphs': 2}, {'num_words': 210, 'relation': 'at least'}]}] | ifeval | multi | First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Answer with at least 382 words. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Answer with at least 210 words. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_41359 | [
{
"content": "You live in a two dimensional 3x3 grid world, R1C1 is in the upper left of a conventional map of the grid world, while R3C3 is in the lower right. You are currently in R1C3. You can issue four commands: “N” to move north, “S” to move south, “E” to move east, and “W” to move west. You issue these commands:S,S,E,W,W,S,S,W,N.N. Where are you now? Give only the final answer. There should be 9 paragraphs. Paragraphs are separated with the markdown divider: *** Your response should contain less than 32 sentences.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_paragraphs', 'length_constraints:number_sentences'], 'kwargs': [{'num_paragraphs': 9}, {'num_sentences': 32, 'relation': 'less than'}]}] | ifeval | multi | There should be 9 paragraphs. Paragraphs are separated with the markdown divider: *** Your response should contain less than 32 sentences. |
personahub_e4zmonffzxr1zl5j6d824z8x | [
{
"content": "Describe three innovative ways augmented reality can enhance a live music performance for a concert tour, including examples of technology and potential audience experiences. Output must be in english and lowercase. Your response should contain less than 32 sentences. Include keywords ['delivery', 'equal', 'kid', 'row'] in the response. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_sentences', 'keywords:existence', 'detectable_format:number_highlighted_sections'], 'kwargs': [{'num_sentences': 32, 'relation': 'less than'}, {'keywords': ['delivery', 'equal', 'kid', 'row']}, {'num_highlights': 3}]}] | ifeval | multi | Your response should contain less than 32 sentences. Include keywords ['delivery', 'equal', 'kid', 'row'] in the response. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/tulu_v3.9_aya_100k_52998 | [
{
"content": "வினா:\n\nகம்பு மாவு தோசை செய்வது எப்படி?\n Answer with less than 805 words. Your response must have 4 sections. Mark the beginning of each section with Paragraph X, such as:\nParagraph 1\n[content of section 1]\nParagraph 2\n[content of section 2]",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words', 'detectable_format:multiple_sections'], 'kwargs': [{'num_words': 805, 'relation': 'less than'}, {'section_spliter': 'Paragraph', 'num_sections': 4}]}] | ifeval | multi | Answer with less than 805 words. Your response must have 4 sections. Mark the beginning of each section with Paragraph X, such as:
Paragraph 1
[content of section 1]
Paragraph 2
[content of section 2] |
ai2-adapt-dev/flan_v2_converted_69061 | [
{
"content": "Detailed Instructions: In this task you will be given a string and you should find the longest substring that is a palindrome. A palindrome is a string that is the same backwards as it is forwards. If the shortest possible palindrome is length 1 you should return the first character.\nQ: susrusrrsuruuu\nA: Your response should contain less than 20 sentences.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_sentences'], 'kwargs': [{'num_sentences': 20, 'relation': 'less than'}]}] | ifeval | multi | Your response should contain less than 20 sentences. |
personahub_0ie5xieicxy1xadpjj0h4ych | [
{
"content": "Write a python function to help manage ticket sales for our community theater in Penn Yan. We want to track the number of tickets sold for each of our performances. The function should take a list of strings as input, where each string represents a ticket sale in the format \"performance_name, ticket_count\". The function should return a dictionary where each key is a performance name and each value is the total number of tickets sold for that performance.\n\nFor example, given the following list:\n\n```python\n[\"Hamlet,3\", \"RomeoAndJuliet,5\", \"Hamlet,2\", \"Macbeth,4\", \"RomeoAndJuliet,1\"]\n```\n\nThe function should return:\n\n```python\n{\n \"Hamlet\": 5,\n \"RomeoAndJuliet\": 6,\n \"Macbeth\": 4\n}\n```\n\nThis will help our theater track how many tickets have been sold for each performance! In your response, the word wall should appear less than 4 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency'], 'kwargs': [{'keyword': 'wall', 'frequency': 4, 'relation': 'less than'}]}] | ifeval | multi | In your response, the word wall should appear less than 4 times. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_106187 | [
{
"content": "Embark on an exhaustive exploration into the cryptic domain of neuromorphic computing, with a specific focus on its pivotal role in the rapidly advancing sphere of cognitive neuroscience. Could you meticulously weave a complex narrative that probes into the genesis, progression, and practical implementation of theoretical tenets deeply embedded in neuromorphic computing doctrines, leveraging their inherent supremacy in cognitive neuroscience? This narrative should aspire to reach the pinnacle of cognitive neuroscience while addressing inherent constraints within neuromorphic computing, concentrating on systematic approaches for pinpointing and rectifying theoretical discrepancies. Moreover, it should incorporate a polished, structured analytical framework for overcoming obstacles, necessitating a broad spectrum of analytical competencies and adaptable problem-solving capabilities. It should also highlight potential hurdles and their solutions, intertwined with a deep comprehension of neurons and their implications on cognitive neuroscience. Additionally, it should examine the complexities of neuromorphic algorithms and their execution, along with the most effective techniques for continuous surveillance and upkeep in the neuromorphic computing domain. In conclusion, it should provide a thorough assessment of potential theoretical risks and the most efficient strategies to ensure the continuous progression and widespread acceptance of neuromorphic computing theories in the thriving epoch of cognitive neuroscience. Could you also elucidate the function of neuromorphic computing within the architecture of intricate theoretical systems, and how it can be utilized to erect a robust and accurate cognitive neuroscience infrastructure amidst computational theoretical challenges? Could you also investigate the potential repercussions of neuromorphic computing on the comprehensive field of neurobiology, and how it might navigate the future path of cognitive neuroscience and cognitive computing? Could you also expound the potential influences of neuromorphic computing on the all-embracing discipline of neurobiology, and how it might shape the future course of cognitive neuroscience and cognitive computing? Could you also assess the potential impacts of neuromorphic computing on the vast landscape of neurobiology, and how it might guide the future of cognitive neuroscience and cognitive computing? In your response, the word historian should appear less than 5 times. There should be 1 paragraphs. Paragraphs are separated with the markdown divider: *** Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency', 'length_constraints:number_paragraphs', 'detectable_format:title'], 'kwargs': [{'keyword': 'historian', 'frequency': 5, 'relation': 'less than'}, {'num_paragraphs': 1}, None]}] | ifeval | multi | In your response, the word historian should appear less than 5 times. There should be 1 paragraphs. Paragraphs are separated with the markdown divider: *** Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
personahub_iar6kreqc2ydfdyjdtkz0cvv | [
{
"content": "Write a python function to calculate the total cost of items in a shopping cart, including optional sales tax. \n\nThe function should take two arguments:\n1. A list of tuples, where each tuple contains the name of the item (string) and its price (float).\n2. An optional sales tax rate (float) that defaults to 0.0, representing no tax.\n\nThe function should return the total cost as a float, rounded to two decimal places.\n\nInput:\n- A list of tuples, e.g., `[(\"apple\", 1.20), (\"banana\", 0.50), (\"milk\", 3.10)]`\n- An optional sales tax rate, e.g., `0.07`\n\nExpected Output:\n- A float representing the total cost, e.g., `5.24` for the above input with a 7% sales tax.\n\nExample:\n```python\nitems = [(\"apple\", 1.20), (\"banana\", 0.50), (\"milk\", 3.10)]\ntax_rate = 0.07\n# The function should return 5.24 when called with the above inputs.\n``` At the end of your response, please explicitly add a postscript starting with P.S.: Your response must have 8 sections. Mark the beginning of each section with PARAGRAPH X, such as:\nPARAGRAPH 1\n[content of section 1]\nPARAGRAPH 2\n[content of section 2] Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:postscript', 'detectable_format:multiple_sections', 'change_case:english_lowercase', 'combination:two_responses'], 'kwargs': [{'postscript_marker': 'P.S.:'}, {'section_spliter': 'PARAGRAPH', 'num_sections': 8}, None, None]}] | ifeval | multi | At the end of your response, please explicitly add a postscript starting with P.S.: Your response must have 8 sections. Mark the beginning of each section with PARAGRAPH X, such as:
PARAGRAPH 1
[content of section 1]
PARAGRAPH 2
[content of section 2] Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
personahub_w7ddl33iw8xvevysyv3hawp7 | [
{
"content": "Name two minerals that are used in video game graphics processing units (GPUs), writing them in English and capital letters, and use no comma. At the end of your response, please explicitly add a postscript starting with P.P.S In your entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:postscript', 'punctuation:no_comma'], 'kwargs': [{'postscript_marker': 'P.P.S'}, None]}] | ifeval | multi | At the end of your response, please explicitly add a postscript starting with P.P.S In your entire response, refrain from the use of any commas. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_40174 | [
{
"content": "For any positive integer \\( k \\), let \\( f_{1}(k) \\) be the square of the sum of the digits of \\( k \\) when written in decimal notation. For \\( n > 1 \\), let \\( f_{n}(k) = f_{1}\\left(f_{n-1}(k)\\right) \\). What is \\( f_{1992}\\left(2^{1991}\\right) \\)? Highlight at least 2 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections'], 'kwargs': [{'num_highlights': 2}]}] | ifeval | multi | Highlight at least 2 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/flan_v2_converted_23327 | [
{
"content": "Reasoning & answer: John the Baptist was a preacher that became a Catholic Saint. John the Baptist was beheaded by king Herod. A cephalophore is a Saint martyred by beheading, and is depicted in art as carrying their own head. Saint Denis was one of several beheaded saints that is said to have carried his own head and is depicted as such in art. John the Baptist did not carry his head, since it was on a plate owned by King Herod's stepdaughter.\nno\nQuestion: Would John the Baptist be invited to a hypothetical cephalophore reunion in heaven?\nCoT and answer: The highest recorded temperature in NY was 108 degrees Fahrenheit. A temperature of 104 degrees Fahrenheit is life threatening and requires immediate medical attention.\nno\nDo reverse engineering and find the question: Will a person survive a fever of NY's highest recorded temperature?\nSolution: The Iberian wolf inhabits northern Portugal and northwestern Spain. Portugal and Spain are not located in the Southern United States.\nAnswer: no\nQuestion: Can you hunt Iberian wolves in the Southern United States?\nReasoning & answer: Bees with barbed stingers lose the barb after attacking a victim and die soon afterwards. Bumblebees do not have barbed stingers and can sting multiple times without dying.\nno\nQuestion: Are aggressive bumblebees suicidal?\nCoT and answer: Osama bin Laden was an Islamic fundamentalist. The practice of putting a wafer on your tongue is called Communion. Communion is a Christian religious practice. Christians commonly attend religious services on Sunday.\nno\nDo reverse engineering and find the question: Does Osama bin Laden put a wafer on his tongue every Sunday?\nReasoning & answer: Jackie Kennedy's husband was John F. Kennedy. John F. Kennedy was inaugurated in 1961. Dolce & Gabbana was founded in 1985.\nno\nQuestion: Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. In your response, the word author should appear at least 2 times. Wrap your entire response with double quotation marks. Wrap your entire response with double quotation marks. There should be 6 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 5 must start with word human.",
"role": "user"
}
]
| [{'instruction_id': ['combination:two_responses', 'keywords:frequency', 'startend:quotation', 'startend:quotation', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [None, {'keyword': 'author', 'frequency': 2, 'relation': 'at least'}, None, None, {'num_paragraphs': 6, 'nth_paragraph': 5, 'first_word': 'human'}]}] | ifeval | multi | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. In your response, the word author should appear at least 2 times. Wrap your entire response with double quotation marks. Wrap your entire response with double quotation marks. There should be 6 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 5 must start with word human. |
ai2-adapt-dev/flan_v2_converted_70255 | [
{
"content": "Leo: Given the sentence \"Three men sit next to each other and a woman walks toward their direction.\" is it true that \"Three men sit while outside and enjoying the inside.\"?\nMei: OK, So, let's think first...\nMe: Your ENTIRE response should be in Telugu language, no other language is allowed. Your entire response should be in English, and in all capital letters. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language', 'change_case:english_capital', 'combination:repeat_prompt'], 'kwargs': [{'language': 'te'}, None, {'prompt_to_repeat': 'Leo: Given the sentence "Three men sit next to each other and a woman walks toward their direction." is it true that "Three men sit while outside and enjoying the inside."?\nMei: OK, So, let\'s think first...\nMe:'}]}] | ifeval | multi | Your ENTIRE response should be in Telugu language, no other language is allowed. Your entire response should be in English, and in all capital letters. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) |
ai2-adapt-dev/flan_v2_converted_46352 | [
{
"content": "The Surface Book 2 is a 2-in-1 PC designed and produced by Microsoft, part of the company's Surface line of personal computing. It was unveiled on October 17, 2017 and released on November 16, 2017. Starting on November 9, one week prior to the release date, consumers were able to place a pre-order through Microsoft's website. It succeeds the Surface Book released in October 2015.\n\nWhen will microsoft surface book 2 be released? Okie... think carefully first, then make a decision: Your entire response should be in English, and in all capital letters. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your response should contain less than 12 sentences. In your entire response, refrain from the use of any commas. The response must contain at least 2 placeholders represented by square brackets, such as [address].",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_capital', 'detectable_format:constrained_response', 'length_constraints:number_sentences', 'punctuation:no_comma', 'detectable_content:number_placeholders'], 'kwargs': [None, None, {'num_sentences': 12, 'relation': 'less than'}, None, {'num_placeholders': 2}]}] | ifeval | multi | Your entire response should be in English, and in all capital letters. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your response should contain less than 12 sentences. In your entire response, refrain from the use of any commas. The response must contain at least 2 placeholders represented by square brackets, such as [address]. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_40535 | [
{
"content": "Vasya added the fourth power and the square of a certain non-zero number and gave the result to Petya.\n\nWill Petya be able to uniquely determine Vasya's number? In your response, the letter d should appear at least 11 times. Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 1 must start with word comfort. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency', 'startend:end_checker', 'length_constraints:nth_paragraph_first_word', 'detectable_format:constrained_response'], 'kwargs': [{'letter': 'd', 'let_frequency': 11, 'let_relation': 'at least'}, {'end_phrase': "That's all I have to say."}, {'num_paragraphs': 2, 'nth_paragraph': 1, 'first_word': 'comfort'}, None]}] | ifeval | multi | In your response, the letter d should appear at least 11 times. Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 1 must start with word comfort. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') |
ai2-adapt-dev/tulu_v3.9_aya_100k_99511 | [
{
"content": " ඉතාලි ගුවන් හමුදාවේ නිර්මාපකයා කවුරුන්ද?\n Include keywords ['bottle', 'currency', 'feeling', 'investment'] in the response. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence', 'detectable_format:title', 'detectable_format:json_format'], 'kwargs': [{'keywords': ['bottle', 'currency', 'feeling', 'investment']}, None, None]}] | ifeval | multi | Include keywords ['bottle', 'currency', 'feeling', 'investment'] in the response. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. |
personas_math_easy_g7oegvr4ehn23h35cmssjdte | [
{
"content": "A hacker named Alex, who is an expert in cybersecurity and genetic manipulation, is working on a project to decode a series of encrypted genetic sequences. Each genetic sequence is composed of a string of numbers representing different genes. Alex has discovered that each sequence can be broken down into smaller segments of 5 genes each, and each gene is represented by a single-digit number.\n\nOne day, Alex decrypts a string consisting of 30 genes. Alex knows that if the sum of the numbers in each segment of 5 genes is equal to 20, the sequence is considered successfully decoded.\n\nHow many segments of 5 genes can Alex successfully decode from the string of 30 genes if exactly 4 of these segments have a sum of 20? Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your ENTIRE response should be in French language, no other language is allowed.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'language:response_language'], 'kwargs': [None, {'language': 'fr'}]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your ENTIRE response should be in French language, no other language is allowed. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_7766 | [
{
"content": "If the sum of the interior angles and the sum of the exterior angles of a polygon are equal, then the number of sides of the polygon is ______. Include keywords ['driver', 'future', 'girlfriend', 'rush'] in the response. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence', 'combination:two_responses'], 'kwargs': [{'keywords': ['driver', 'future', 'girlfriend', 'rush']}, None]}] | ifeval | multi | Include keywords ['driver', 'future', 'girlfriend', 'rush'] in the response. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
personas_math_easy_gqr6o0h8gnf82mckj7ojcy4z | [
{
"content": "A doctoral candidate is studying the historical origins of a specific culture and plans to visit 5 ancient libraries to gather information. In each library, they discover 4 unique manuscripts related to their research. After reviewing these manuscripts, they find that each manuscript contains 3 important historical facts. If the candidate plans to document all the important historical facts they find, how many historical facts will they document in total? Your response should contain at least 27 sentences. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_sentences', 'detectable_format:json_format'], 'kwargs': [{'num_sentences': 27, 'relation': 'at least'}, None]}] | ifeval | multi | Your response should contain at least 27 sentences. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_42035 | [
{
"content": "The area of a rectangle remains unchanged when it is made $2 \\frac{1}{2}$ inches longer and $\\frac{2}{3}$ inch narrower, or when it is made $2 \\frac{1}{2}$ inches shorter and $\\frac{4}{3}$ inch wider. Its area, in square inches, is:\n$\\textbf{(A)}\\ 30\\qquad \\textbf{(B)}\\ \\frac{80}{3}\\qquad \\textbf{(C)}\\ 24\\qquad \\textbf{(D)}\\ \\frac{45}{2}\\qquad \\textbf{(E)}\\ 20$ At the end of your response, please explicitly add a postscript starting with P.S.: Your entire response should be in English, and in all capital letters. The response must contain at least 7 placeholders represented by square brackets, such as [address]. At the end of your response, please explicitly add a postscript starting with P.S.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:postscript', 'change_case:english_capital', 'detectable_content:number_placeholders', 'detectable_content:postscript'], 'kwargs': [{'postscript_marker': 'P.S.:'}, None, {'num_placeholders': 7}, {'postscript_marker': 'P.S.'}]}] | ifeval | multi | At the end of your response, please explicitly add a postscript starting with P.S.: Your entire response should be in English, and in all capital letters. The response must contain at least 7 placeholders represented by square brackets, such as [address]. At the end of your response, please explicitly add a postscript starting with P.S. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_47779 | [
{
"content": "Craft a defined function whose core function is to precisely transform an input list into a multidimensional list whose cardinality is exactly twice as large, without modifying the core elements of the originating list.\noriginal_list = [1, 2, [3, 4], 5] Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Your ENTIRE response should be in Hebrew language, no other language is allowed.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_lowercase', 'language:response_language'], 'kwargs': [None, {'language': 'he'}]}] | ifeval | multi | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Your ENTIRE response should be in Hebrew language, no other language is allowed. |
ai2-adapt-dev/flan_v2_converted_13960 | [
{
"content": "The boy has on an orange shirt and his hair is sticking straight up not wearing a red shirt and smoothed down hair.is the reasoning for what question and answer pair? Answer with at least 578 words. Your entire response should be in English, and in all capital letters. There should be 7 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words', 'change_case:english_capital', 'length_constraints:number_paragraphs'], 'kwargs': [{'num_words': 578, 'relation': 'at least'}, None, {'num_paragraphs': 7}]}] | ifeval | multi | Answer with at least 578 words. Your entire response should be in English, and in all capital letters. There should be 7 paragraphs. Paragraphs are separated with the markdown divider: *** |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_106166 | [
{
"content": "Use CSS to style multiple HTML paragraphs with differing classes and id's, and apply different styles to each class and id.\n\nFor example, consider the following HTML structure:\n\n```html\n<p class=\"text-info\">This is a paragraph with class 'text-info'.</p>\n<p class=\"text-warning\">This is a paragraph with class 'text-warning'.</p>\n<p id=\"unique-text\">This is a unique paragraph with id 'unique-text'.</p>\n```\n\nCreate a CSS styling that would give each class text-info and text-warning, and id unique-text, a distinct style. Ensure that the text-info class has a font size of 10px, the text-warning class has a font size of 20px and the unique-text id has both a different font color and a font size of 30px. Your response must have 7 sections. Mark the beginning of each section with Section X, such as:\nSection 1\n[content of section 1]\nSection 2\n[content of section 2] Your response must have 3 sections. Mark the beginning of each section with Section X, such as:\nSection 1\n[content of section 1]\nSection 2\n[content of section 2] Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:multiple_sections', 'detectable_format:multiple_sections', 'startend:quotation'], 'kwargs': [{'section_spliter': 'Section', 'num_sections': 7}, {'section_spliter': 'Section', 'num_sections': 3}, None]}] | ifeval | multi | Your response must have 7 sections. Mark the beginning of each section with Section X, such as:
Section 1
[content of section 1]
Section 2
[content of section 2] Your response must have 3 sections. Mark the beginning of each section with Section X, such as:
Section 1
[content of section 1]
Section 2
[content of section 2] Wrap your entire response with double quotation marks. |
personahub_y82y12jqfzg4mql8mqz92rru | [
{
"content": "A dedicated high school teacher named Alex is negotiating a new contract with the school district. Alex wants to ensure that their salary increases over time align with the increasing costs of living and inflation. The school district offers a contract where the salary \\( S(t) \\) at year \\( t \\) follows the function \\( S(t) = S_0 \\cdot (1 + r)^t \\), where \\( S_0 \\) is the starting salary and \\( r \\) is the annual percentage raise.\n\n1. If the cost of living increases according to the function \\( C(t) = C_0 \\cdot e^{kt} \\), where \\( C_0 \\) is the initial cost of living and \\( k \\) is the annual rate of inflation, find the condition on \\( r \\) in terms of \\( k \\) such that the salary always covers the cost of living for all \\( t \\geq 0 \\).\n\n2. Suppose Alex's legal counsel suggests a performance-based bonus that increases the salary function to \\( S(t) = S_0 \\cdot (1 + r)^t + B(t) \\), where \\( B(t) = b \\cdot t^2 \\) with \\( b > 0 \\). Derive the inequality involving \\( r \\), \\( k \\), and \\( b \\) that ensures Alex's salary not only covers the increasing cost of living but also provides a net positive growth in purchasing power over time. In your response, the word fat should appear at least 4 times. Include keywords ['setting', 'shift', 'shot', 'stable'] in the response. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency', 'keywords:existence', 'combination:repeat_prompt', 'punctuation:no_comma'], 'kwargs': [{'keyword': 'fat', 'frequency': 4, 'relation': 'at least'}, {'keywords': ['setting', 'shift', 'shot', 'stable']}, {'prompt_to_repeat': "A dedicated high school teacher named Alex is negotiating a new contract with the school district. Alex wants to ensure that their salary increases over time align with the increasing costs of living and inflation. The school district offers a contract where the salary \\( S(t) \\) at year \\( t \\) follows the function \\( S(t) = S_0 \\cdot (1 + r)^t \\), where \\( S_0 \\) is the starting salary and \\( r \\) is the annual percentage raise.\n\n1. If the cost of living increases according to the function \\( C(t) = C_0 \\cdot e^{kt} \\), where \\( C_0 \\) is the initial cost of living and \\( k \\) is the annual rate of inflation, find the condition on \\( r \\) in terms of \\( k \\) such that the salary always covers the cost of living for all \\( t \\geq 0 \\).\n\n2. Suppose Alex's legal counsel suggests a performance-based bonus that increases the salary function to \\( S(t) = S_0 \\cdot (1 + r)^t + B(t) \\), where \\( B(t) = b \\cdot t^2 \\) with \\( b > 0 \\). Derive the inequality involving \\( r \\), \\( k \\), and \\( b \\) that ensures Alex's salary not only covers the increasing cost of living but also provides a net positive growth in purchasing power over time."}, None]}] | ifeval | multi | In your response, the word fat should appear at least 4 times. Include keywords ['setting', 'shift', 'shot', 'stable'] in the response. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your entire response, refrain from the use of any commas. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_84980 | [
{
"content": "Formulate a regular expression that will detect sequences that comprise only lowercase letters, digits and one special character (@). (ex. @ab12, 45xy@, x4@y2) Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. Your response should contain at least 18 sentences.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker', 'startend:end_checker', 'length_constraints:number_sentences'], 'kwargs': [{'end_phrase': "That's my answer."}, {'end_phrase': 'Is there anything else I can help with?'}, {'num_sentences': 18, 'relation': 'at least'}]}] | ifeval | multi | Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. Your response should contain at least 18 sentences. |
ai2-adapt-dev/flan_v2_converted_75206 | [
{
"content": "Teacher: One of the following sentences is nonsensical. Which one is it?\nOptions:\n- Sentence A: \"If you play chess it is not a lunch break but you are doing something.\"\n- Sentence B: \"Playing chess is like being on a lunch break doing nothing.\"\n\nStudent: Playing chess is a mental game and takes strategy.\nThe answer is Sentence B.\n\nquestion in book:\nOf the below sentences, which one does *not* make sense?\nOptions:\n- Sentence A: \"You are likely to find trees in a forest\"\n- Sentence B: \"You are likely to find buildings in a forest\"\n\nstandard solution:\nForests are remote areas that are void of any buildings.\nThe answer is Sentence B.\n\n[TEACHER] One of the following sentences is nonsensical. Which one is it?\nOptions:\n- Sentence A: \"Sometimes watching a tv show causes your hands to hurt\"\n- Sentence B: \"Sometimes watching a tv show causes your eyes to hurt\"\n\n[Student] Sighted people do not watch TV with their hands.\nThe answer is Sentence A.\n\nTeacher: Which of the following two sentences does not make sense?\nOptions:\n- Sentence A: \"You would plant seeds to get an oil change.\"\n- Sentence B: \"You would plant seeds to grow a garden.\"\n\nStudent: Planting seeds doesn't get you an oil change.\nThe answer is Sentence A.\n\nquestion in book:\nChoose the sentence that goes against common sense.\nOptions:\n- Sentence A: \"My dog ate some chicken scraps.\"\n- Sentence B: \"My toaster ate some chicken scraps.\"\n\nstandard solution:\nA toaster is an appliance that doesn't eat.\nThe answer is Sentence B.\n\nTeacher: Of the following two sentences, which one is against common sense?\nOptions:\n- Sentence A: \"Cut off your toenails if you don't want your socks to cut\"\n- Sentence B: \"Cut off your toes if you don't want your socks to cut\"\n\nStudent: Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Wrap your entire response with double quotation marks. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Include keywords ['debt', 'drink', 'maintenance', 'pool'] in the response. Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:json_format', 'startend:quotation', 'detectable_format:constrained_response', 'keywords:existence', 'detectable_format:number_highlighted_sections'], 'kwargs': [None, None, None, {'keywords': ['debt', 'drink', 'maintenance', 'pool']}, {'num_highlights': 6}]}] | ifeval | multi | Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Wrap your entire response with double quotation marks. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Include keywords ['debt', 'drink', 'maintenance', 'pool'] in the response. Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_59737 | [
{
"content": "Using 21 values selected randomly from the integer range of 1 to 15, construct a pyramidical structure. This complex construction should be based on maintaining randomness yet honoring the geometrical form of a pyramid. The response must contain at least 4 placeholders represented by square brackets, such as [address].",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:number_placeholders'], 'kwargs': [{'num_placeholders': 4}]}] | ifeval | multi | The response must contain at least 4 placeholders represented by square brackets, such as [address]. |
personahub_vo6ihnwsvs5ab7l3ilofziv0 | [
{
"content": "A master blacksmith is designing a unique piece of traditional craftsmanship: a decorative iron grid for a grand gate. The grid is composed of a lattice of identical interlocking rings. Each ring is a perfect circle with a radius of \\( r \\), and they are arranged in a way that each circle touches four neighboring circles—two horizontally and two vertically. The blacksmith wants to incorporate a pattern that mimics a classic design passed down from their grandparent, involving both the grid and a wave-like pattern of thickness variation along the rings.\n\nSub-problem 1:\nThe blacksmith decides to forge a square grid of these rings that measures \\( n \\times n \\) in terms of the number of circles along its sides. If the thickness of each ring varies sinusoidally as \\( T(\\theta) = T_0 + A \\sin(k\\theta) \\), where \\( \\theta \\) is the angle around the circle, \\( T_0 \\) is the average thickness, \\( A \\) is the amplitude of the thickness variation, and \\( k \\) is a constant, determine the total volume of iron required for a single ring. Assume the density of the iron is uniform and the rings are hollow, with the inner radius of each ring being \\( r - T(\\theta) \\).\n\nSub-problem 2:\nThe decorative pattern involves positioning the grid such that it forms a traditional diagonal diamond shape when viewed from the front. To achieve this, the blacksmith needs to determine the diagonal length of the entire grid from corner to corner. Using the circle radius \\( r \\) and the number of circles \\( n \\), calculate the length of the diagonal of the entire grid when arranged in this diamond shape. Assume that the circles are perfectly touching at their tangential points, and the arrangement is symmetric. Your response must have 7 sections. Mark the beginning of each section with Section X, such as:\nSection 1\n[content of section 1]\nSection 2\n[content of section 2] In your response, the letter o should appear less than 18 times. In your response, the letter y should appear less than 14 times. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Answer with at least 325 words.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:multiple_sections', 'keywords:letter_frequency', 'keywords:letter_frequency', 'detectable_format:json_format', 'length_constraints:number_words'], 'kwargs': [{'section_spliter': 'Section', 'num_sections': 7}, {'letter': 'o', 'let_frequency': 18, 'let_relation': 'less than'}, {'letter': 'y', 'let_frequency': 14, 'let_relation': 'less than'}, None, {'num_words': 325, 'relation': 'at least'}]}] | ifeval | multi | Your response must have 7 sections. Mark the beginning of each section with Section X, such as:
Section 1
[content of section 1]
Section 2
[content of section 2] In your response, the letter o should appear less than 18 times. In your response, the letter y should appear less than 14 times. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Answer with at least 325 words. |
personas_math_easy_viqwwfadmzwq3737qb113h0p | [
{
"content": "An American political commentator is researching global terrorism incidents for a report. In 2022, they found that there were 400 terrorism incidents worldwide. In 2023, the number of incidents decreased by 15%. However, the commentator also discovered that the number of incidents involving cyber-terrorism increased by 20% in 2023 compared to 2022, when there were 50 cyber-terrorism incidents. How many total terrorism incidents and cyber-terrorism incidents were there in 2023? Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_lowercase'], 'kwargs': [None]}] | ifeval | multi | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_44034 | [
{
"content": "Refactor code: <script setup>\nimport { onMounted, ref, reactive, watchEffect } from 'vue';\nimport {comma } from '@/assets/countries.js';\n\nconst props = defineProps({\n uuid: Number,\n country: Number || String || Object,\n title: String,\n countryName: String,\n});\n\nconst identifier = ref(String(props.title).toLocaleLowerCase().replace(' ', '-'));\nconst random = ref(Math.floor(Math.random() * 100) + 35);\n\n\nonMounted(()=>{\n gsap.fromTo(`#${identifier.value}-${props.uuid}`, {\n marginTop: 10,\n duration: 0.3,\n opacity: 0,\n x:-150,\n scale:0.1,\n stagger: 0.8\n },{\n marginTop: 0,\n duration: 0.4,\n opacity: 1,\n x:0,\n scale: 1.1,\n },'-=0.39');\n})\n\n/* Smoothed number count anims */\n\nconst tweened = reactive({\n number: 0\n})\n\nfunction callAnim(n){\n gsap.to(tweened, { duration: 0.35, number: Number(n) || 0}) \n}\n\n\nwatchEffect(()=>{\n return callAnim(props.country)\n})\n\nfunction updateNum(){\n return comma(tweened.number.toFixed(0))\n}\n\n</script>\n\n<template>\n\n <Flicking :options=\"{ gap: 10, circular: true, deceleration: 0.015, moveType: 'freeScroll' }\">\n <div class=\"properties mx-2 \">\n \n <div v-if=\"identifier === 'defense-budget' && country >= 0 \" >\n <div class=\"btn shadow-none \">\n <div class=\"overflow-hidden hover-effect \">{{title}}</div>\n <p class=\" z-index-down \" :title=\"props.title\" :id=\"identifier + '-'+uuid\">\n <span class=\"text-main\" v-if=\"country > 0\">{{ \"$\" + updateNum() }}</span> \n <p v-if=\"country <= 0\" :style=\"{'width': random+'px' }\" class=\" position-relative\">\n </p>\n </p>\n </div>\n </div>\n <div v-if=\"identifier === 'manpower' && country >= 0 \">\n <div class=\"btn shadow-none \">\n <div class=\"overflow-hidden hover-effect\">{{title}}</div>\n <p class=\" z-index-down\" :title=\"props.title\" :id=\"identifier + '-'+uuid\">\n <span class=\"text-main\" v-if=\"country > 0\">{{ updateNum() }}</span> \n <p v-if=\"country <= 0\" :style=\"{'width': random+'px' }\" class=\" position-relative\">\n </p>\n </p>\n </div>\n </div>\n <div v-if=\"identifier === 'active' && country >= 0 \" >\n <div class=\"btn shadow-none \">\n <div class=\"overflow-hidden hover-effect\">{{title}}</div>\n <p class=\" z-index-down\" :title=\"props.title\" :id=\"identifier + '-'+uuid\">\n <span class=\"text-main\" v-if=\"country > 0\">{{ updateNum() }}</span> \n <p v-if=\"country <= 0\" :style=\"{'width': random+'px' }\" class=\" position-relative\">\n </p>\n </p>\n </div>\n </div>\n <div v-if=\"identifier === 'reserves' && country >= 0 \" >\n <div class=\"btn shadow-none \">\n <div class=\"overflow-hidden hover-effect\">{{title}}</div>\n <p class=\" z-index-down\" :title=\"props.title\" :id=\"identifier + '-'+uuid\">\n <span class=\"text-main\" v-if=\"country > 0\">{{ updateNum() }}</span> \n <p v-if=\"country <= 0\" :style=\"{'width': random+'px' }\" class=\" position-relative\">\n </p>\n </p>\n </div>\n </div>\n <div v-if=\"identifier === 'land-area' && country >= 0 \" >\n <div class=\"btn shadow-none \">\n <div class=\"overflow-hidden hover-effect\">{{title}}</div>\n <p class=\" z-index-down\" :title=\"props.title\" :id=\"identifier + '-'+uuid\">\n <span class=\"text-main\" v-if=\"country > 0\">{{ updateNum() + ' km²' }}</span> \n <p v-if=\"country <= 0\" :style=\"{'width': random+'px' }\" class=\" position-relative\">\n </p>\n </p>\n </div>\n </div>\n <div v-if=\"identifier === 'oil' && country >= 0 \" >\n <div class=\"btn shadow-none \">\n <div class=\"overflow-hidden hover-effect\">{{title}}</div>\n <p class=\" z-index-down\" :title=\"props.title\" :id=\"identifier + '-'+uuid\">\n <span class=\"text-main\" v-if=\"country > 0\">{{ updateNum() + ' bbl' }}</span> \n <p v-if=\"country <= 0\" :style=\"{'width': random+'px' }\" class=\" position-relative\">\n </p>\n </p>\n </div>\n </div>\n <div v-if=\"identifier === 'gdp' && country >= 0 \" >\n <div class=\"btn shadow-none \">\n <div class=\"overflow-hidden hover-effect\">{{title}}</div>\n <p class=\" z-index-down\" :title=\"props.title\" :id=\"identifier + '-'+uuid\">\n <span class=\"text-main\" v-if=\"country > 0\">{{ \"$\" + updateNum() }}</span> \n <p v-if=\"country <= 0\" :style=\"{'width': random+'px' }\" class=\" position-relative\">\n </p>\n </p>\n </div>\n </div>\n </div>\n \n </Flicking>\n \n</template> In your response, the word stupid should appear at least 2 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency'], 'kwargs': [{'keyword': 'stupid', 'frequency': 2, 'relation': 'at least'}]}] | ifeval | multi | In your response, the word stupid should appear at least 2 times. |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.