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
|
|---|---|---|---|---|---|
ai2-adapt-dev/flan_v2_converted_33496 | [
{
"content": "Question: Pick which sentence is not logical.\nOptions:\n- Sentence A: \"The man hit the baseball with his bat.\"\n- Sentence B: \"The bat hit the man with a baseball.\"\n\nPlease answer this question gradually: In your response, the word evening should appear less than 6 times. Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. There should be 9 paragraphs. Paragraphs are separated with the markdown divider: *** Answer with at least 928 words.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency', 'detectable_format:number_highlighted_sections', 'length_constraints:number_paragraphs', 'length_constraints:number_words'], 'kwargs': [{'keyword': 'evening', 'frequency': 6, 'relation': 'less than'}, {'num_highlights': 5}, {'num_paragraphs': 9}, {'num_words': 928, 'relation': 'at least'}]}] | ifeval | multi | In your response, the word evening should appear less than 6 times. Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. There should be 9 paragraphs. Paragraphs are separated with the markdown divider: *** Answer with at least 928 words. |
personahub_3kqmnwzgh4nh9d7w15qlzxfb | [
{
"content": "An astronomer is analyzing the spectral data from a star in a distant galaxy to determine its chemical composition. The astronomer uses the spectral lines to identify the presence of different elements and their relative abundances. The light from the star takes 2 million years to reach Earth, and the star is part of a galaxy moving away from Earth at a velocity of 3000 km/s due to the expansion of the universe.\n\n1. Given that the redshift \\( z \\) is related to the velocity \\( v \\) by the equation \\( z = \\frac{v}{c} \\), where \\( c \\) is the speed of light (approximately \\( 3 \\times 10^5 \\) km/s), calculate the redshift \\( z \\) of the galaxy. \n\n2. The astronomer detects a spectral line at a wavelength of \\( 656.3 \\) nm in the laboratory (known as the H-alpha line of hydrogen). Using the redshift calculated in sub-problem 1, determine the observed wavelength of this spectral line as it appears in the astronomer's data. 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/evol_codealpaca_heval_decontaminated_15384 | [
{
"content": "I have a pyspark datafrme like below\n\n+---+-------------------------------------------------------------------------------+\n|id |strval |\n+---+-------------------------------------------------------------------------------+\n|1 |{\"position\":\"left\",\"title\":\"journeys\",\"link\":\"https://www.abcd.com\",\"rank\":549}|\n|2 |{\"position\":\"left\",\"title\":\"journeys\",\"link\":\"https://www.abcd.com\",\"rank\":5} |\n+---+-------------------------------------------------------------------------------+\n\n\nI want to find only the value of rank using the regexp\nI have tried below code\n\nselect id,\nregexp_extract(\"strval\", '(\\\"rank\\\":)(\\d+)',2) as rn\nfrom tbl\n\n\nbut all I am getting is empty values.\nCan someone please guide me to achieve this? Answer with at least 637 words. Do not include keywords ['drama', 'purpose', 'risk', 'town'] in the response. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Your response must have 4 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': ['length_constraints:number_words', 'keywords:forbidden_words', 'change_case:english_lowercase', 'detectable_format:multiple_sections'], 'kwargs': [{'num_words': 637, 'relation': 'at least'}, {'forbidden_words': ['drama', 'purpose', 'risk', 'town']}, None, {'section_spliter': 'Section', 'num_sections': 4}]}] | ifeval | multi | Answer with at least 637 words. Do not include keywords ['drama', 'purpose', 'risk', 'town'] in the response. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Your response must have 4 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/evol_codealpaca_heval_decontaminated_13503 | [
{
"content": "Ponder upon quadratic Diophantine equations of the following structure:\n$$x^2 - Dy^2 = 1$$\nFor instance, when $D=13$, the smallest solution in terms of $x$ is $649^2 - 13 \\times 180^2 = 1$.\nIt can be safely assumed that there are no solutions in positive integers when $D$ is a perfect square.\nBy determining the smallest solutions in terms of $x$ for $D = \\{2, 3, 5, 6, 7\\}$, we derive the following:\n\\begin{align}\n3^2 - 2 \\times 2^2 &= 1\\\\\n2^2 - 3 \\times 1^2 &= 1\\\\\n{\\color{red}{\\mathbf 9}}^2 - 5 \\times 4^2 &= 1\\\\\n5^2 - 6 \\times 2^2 &= 1\\\\\n8^2 - 7 \\times 3^2 &= 1\n\\end{align}\nTherefore, by considering the smallest solutions in terms of $x$ for $D \\le 7$, the greatest $x$ is obtained when $D=5$.\nDetermine the value of $D \\le 1000$ in the smallest solutions of $x$ for which the greatest value of $x$ is achieved. Your response must have 10 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] 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 function.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:multiple_sections', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [{'section_spliter': 'Sec.', 'num_sections': 10}, {'num_paragraphs': 8, 'nth_paragraph': 4, 'first_word': 'function'}]}] | ifeval | multi | Your response must have 10 sections. Mark the beginning of each section with Sec. X, such as:
Sec. 1
[content of section 1]
Sec. 2
[content of section 2] 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 function. |
personas_math_easy_4rq7alhja2vxuh4apjbna6nv | [
{
"content": "Alex, a young and skeptical freelance writer, has decided to invest in her own retirement plan instead of relying on a traditional pension. She plans to save a portion of her freelance income each month. This month, Alex earned $2,500 from her writing projects. She decides to save 15% of her income for her retirement plan. Additionally, she receives a bonus of $200 for a special project and wants to save half of this bonus for her retirement as well. How much money will Alex have saved for her retirement plan by the end of this month? In your response, the word dog should appear less than 5 times. Your response should contain at least 19 sentences. Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. In your entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency', 'length_constraints:number_sentences', 'detectable_format:number_highlighted_sections', 'punctuation:no_comma'], 'kwargs': [{'keyword': 'dog', 'frequency': 5, 'relation': 'less than'}, {'num_sentences': 19, 'relation': 'at least'}, {'num_highlights': 5}, None]}] | ifeval | multi | In your response, the word dog should appear less than 5 times. Your response should contain at least 19 sentences. Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. In your entire response, refrain from the use of any commas. |
personas_math_easy_2zl8njm84whnm1st4lmo2tzy | [
{
"content": "A small town photographer is inspired by Jordi's works and decides to create a photo exhibition in the local community hall. The photographer plans to display 5 different series of photos, each series having 8 photos. To match Jordi's style, the photographer wants to add an additional 3 decorative frames to each series. If each photo and each frame costs $10 to print and prepare, how much will the photographer spend in total for the exhibition? Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. 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.') 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: ******.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_lowercase', 'detectable_format:constrained_response', 'combination:repeat_prompt', 'combination:two_responses'], 'kwargs': [None, None, {'prompt_to_repeat': "A small town photographer is inspired by Jordi's works and decides to create a photo exhibition in the local community hall. The photographer plans to display 5 different series of photos, each series having 8 photos. To match Jordi's style, the photographer wants to add an additional 3 decorative frames to each series. If each photo and each frame costs $10 to print and prepare, how much will the photographer spend in total for the exhibition?"}, None]}] | ifeval | multi | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. 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.') 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: ******. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_35668 | [
{
"content": "Generate an etsy title for a art work that can be added to mugs, painting, tshirt, etc within 140 characters with no & only | to separate without first word being whimsical and is the name of the art Cubism Art Do not include keywords ['economy', 'editor', 'female', 'writer'] in the response. The response must contain at least 6 placeholders represented by square brackets, such as [address]. There should be 6 paragraphs. Paragraphs are separated with the markdown divider: *** There should be 6 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
]
| [{'instruction_id': ['keywords:forbidden_words', 'detectable_content:number_placeholders', 'length_constraints:number_paragraphs', 'length_constraints:number_paragraphs'], 'kwargs': [{'forbidden_words': ['economy', 'editor', 'female', 'writer']}, {'num_placeholders': 6}, {'num_paragraphs': 6}, {'num_paragraphs': 6}]}] | ifeval | multi | Do not include keywords ['economy', 'editor', 'female', 'writer'] in the response. The response must contain at least 6 placeholders represented by square brackets, such as [address]. There should be 6 paragraphs. Paragraphs are separated with the markdown divider: *** There should be 6 paragraphs. Paragraphs are separated with the markdown divider: *** |
ai2-adapt-dev/no_robots_converted_2069 | [
{
"content": "Write a paragraph to summarize the history of Calico, California.\n\nIn 1881, four prospectors were leaving Grapevine Station (present day Barstow, California) for a mountain peak to the northeast. After they described the peak as \"calico-colored\", the peak, the mountain range to which it belonged, and the town that followed were all called Calico.[5] The four prospectors discovered silver in the mountain and opened the Silver King Mine, which was California's largest silver producer in the mid-1880s.[5][6] John C. King, who had grubstaked the prospectors who discovered the silver vein (the Silver King Mine was thus named after him), was the uncle of Walter Knott founder of Knott's Berry Farm. \n\nKing was sheriff of San Bernardino County from 1879 to 1882.[7][8][9][10] A post office at Calico was established in early 1882, and the Calico Print, a weekly newspaper, started publishing. The town soon supported three hotels, five general stores, a meat market, bars, brothels, and three restaurants and boarding houses. The county established a school district and a voting precinct.[11][12] The town also had a deputy sheriff and two constables, two lawyers and a justice of the peace, five commissioners, and two doctors. There was also a Wells Fargo office and a telephone and telegraph service.[5] At its height of silver production during 1883 and 1885,[11] Calico had over 500 mines and a population of 1,200 people.[5] Local badmen were buried in the Boot Hill cemetery.[13][14]\n\nThe discovery of the borate mineral colemanite in the Calico mountains a few years after the settlement of the town also helped Calico's fortunes, and in 1890 the estimated population of the town was 3,500, with nationals of China, England, Ireland, Greece, France, and the Netherlands, as well as Americans living there.[15] In the same year, the Silver Purchase Act was enacted and drove down the price of silver.[5] \n\nBy 1896, its value had decreased to $0.57 per troy ounce, and Calico's silver mines were no longer economically viable.[5] The post office was discontinued in 1898,[16] and the school closed not long after.[11] By the turn of the century, Calico was all but a ghost town,[15] and with the end of borax mining in the region in 1907 the town was completely abandoned.[citation needed] Many of the original buildings were moved to Barstow, Daggett and Yermo.[15]\n\nAn attempt to revive the town was made in about 1915, when a cyanide plant was built to recover silver from the unprocessed Silver King Mine's deposits. Walter Knott and his wife Cordelia, founders of Knott's Berry Farm, were homesteaded at Newberry Springs around this time, and Knott helped build the redwood cyanide tanks for the plant.[15][17] 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 Include keywords ['beach', 'courage', 'feedback', 'word'] in the response. 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:number_bullet_lists', 'keywords:existence', 'detectable_format:constrained_response'], 'kwargs': [{'num_bullets': 2}, {'keywords': ['beach', 'courage', 'feedback', 'word']}, None]}] | 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 Include keywords ['beach', 'courage', 'feedback', 'word'] in the response. 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.') |
personas_math_easy_0uz30xrksmc4lsaxv7gik6vu | [
{
"content": "Jamie, a well-respected PR blogger and influencer, has decided to host a webinar on tips and advice for breaking into the PR industry. She plans to send out invitations to her 2000 newsletter subscribers. Out of those subscribers, she expects 30% will register for the webinar. Jamie also plans to post the registration link on her social media accounts, where she has a combined following of 10,000 people, and she estimates that 5% of her followers will register through social media. How many total people does Jamie expect to register for her webinar? Finish your response with this exact phrase The END.. No other words should follow this phrase. Your response must have 10 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': ['startend:end_checker', 'detectable_format:multiple_sections'], 'kwargs': [{'end_phrase': 'The END.'}, {'section_spliter': 'Paragraph', 'num_sections': 10}]}] | ifeval | multi | Finish your response with this exact phrase The END.. No other words should follow this phrase. Your response must have 10 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_11059 | [
{
"content": "Chain-of-thought: There is no HDMI port in a phone.\n--\nQuestion: Pick which sentence is not logical.\nOptions:\n- Sentence A: \"he charged his phone with a hdmi cable\"\n- Sentence B: \"he charged his phone with a phone cable\"\n\nAnswer: Sentence A\n\nChain-of-thought: A lion is too large to be carried in a basket.\n\nQuestion: Which of these sentences doesn't make sense?\nOptions:\n- Sentence A: \"He carries a banana in basket\"\n- Sentence B: \"He carries lion into the basket\"\n\nAnswer: Sentence B\n\nExplanation for the following question's answer: Blankets do not have words that can be read.\nQuestion: Of the following two sentences, which one is against common sense?\nOptions:\n- Sentence A: \"She read a book.\"\n- Sentence B: \"She read a blanket.\"\n\nAnswer: Sentence B\n\nChain-of-thought: Cement is a building material unsafe for consumption.\n--\nQuestion: Which of the following sentences is nonsensical?\nOptions:\n- Sentence A: \"Drinking green tea increases you lifespan.\"\n- Sentence B: \"Drinking cement increases your lifespan\"\n\nAnswer: Sentence B\n\nChain-of-thought: You can not be in death and still breathing.\n\nQuestion: Pick which sentence is not logical.\nOptions:\n- Sentence A: \"Death happens when you are breathing but never wake up.\"\n- Sentence B: \"Death happens when you are no longer breathing.\"\n\nAnswer: Sentence A\n\nChain-of-thought: An ostrich does not go to the mall.\n--\n Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Include keywords ['issue', 'map', 'plane', 'wait'] in the response. 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 lowercase letters. No capital letters are allowed. In your entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections', 'keywords:existence', 'detectable_content:postscript', 'change_case:english_lowercase', 'punctuation:no_comma'], 'kwargs': [{'num_highlights': 5}, {'keywords': ['issue', 'map', 'plane', 'wait']}, {'postscript_marker': 'P.S.:'}, None, None]}] | ifeval | multi | Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Include keywords ['issue', 'map', 'plane', 'wait'] in the response. 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 lowercase letters. No capital letters are allowed. In your entire response, refrain from the use of any commas. |
personahub_7yp8e9uj42yq4u0ctvbtoktv | [
{
"content": "As a cybersecurity consultant, you are designing an incident response plan that includes the allocation of resources for threat detection and mitigation. You need to ensure that the costs associated with these activities stay within budget while maximizing effectiveness.\n\n1. You have determined that the cost of threat detection (D) and mitigation (M) can be modeled by the quadratic equation: \\( C(x) = 2x^2 - 8x + 10 \\), where \\( x \\) is the number of hours spent on detection activities. If the budget for these activities is $50,000, find the range of values for \\( x \\) that satisfy \\( C(x) \\leq 50,000 \\).\n\n2. In addition to the cost, you want to optimize the balance between detection and mitigation effectiveness. The effectiveness of mitigation activities (E) is inversely proportional to the square of the hours spent on detection. If the effectiveness function is given by \\( E(x) = \\frac{1200}{x^2} \\), find the integer values of \\( x \\) that ensure the effectiveness remains above 30 units. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Do not include keywords ['attack', 'dealer', 'season', 'stock'] in the response. 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 entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['combination:two_responses', 'keywords:forbidden_words', 'detectable_format:number_bullet_lists', 'change_case:english_lowercase'], 'kwargs': [None, {'forbidden_words': ['attack', 'dealer', 'season', 'stock']}, {'num_bullets': 5}, None]}] | ifeval | multi | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Do not include keywords ['attack', 'dealer', 'season', 'stock'] in the response. Your answer must contain exactly 5 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
personahub_puwpgp882sqt6j93edtzyzsv | [
{
"content": "A software development manager is designing a team structure to optimize productivity. She has identified two main tasks: coding (C) and testing (T). The effectiveness of the team is modeled by the function \\( E(n, m) = 10n^2 + 8m^2 + 4nm \\), where \\( n \\) is the number of coders and \\( m \\) is the number of testers. Due to budget constraints, she can hire a maximum of 10 people.\n\n1. Determine the values of \\( n \\) and \\( m \\) that maximize the effectiveness \\( E(n, m) \\) under the constraint \\( n + m \\leq 10 \\).\n\n2. After finding the optimal team composition, the manager realizes that the synergy between coders and testers can be further improved. She models this synergy as an additional term \\( S(n, m) = k \\cdot n \\cdot m \\) in the effectiveness function, where \\( k \\) is a constant representing the degree of synergy. With \\( k = 2 \\), calculate the new optimal values of \\( n \\) and \\( m \\) that maximize the effectiveness \\( E(n, m) + S(n, m) \\) under the same constraint \\( n + m \\leq 10 \\). Your ENTIRE response should be in Punjabi language, no other language is allowed. There should be 9 paragraphs. Paragraphs are separated with the markdown divider: *** 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 1 must start with word engineering. There should be 1 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 breakfast. In your response, words with all capital letters should appear less than 32 times.",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language', 'length_constraints:number_paragraphs', 'length_constraints:nth_paragraph_first_word', 'length_constraints:nth_paragraph_first_word', 'change_case:capital_word_frequency'], 'kwargs': [{'language': 'pa'}, {'num_paragraphs': 9}, {'num_paragraphs': 4, 'nth_paragraph': 1, 'first_word': 'engineering'}, {'num_paragraphs': 1, 'nth_paragraph': 1, 'first_word': 'breakfast'}, {'capital_frequency': 32, 'capital_relation': 'less than'}]}] | ifeval | multi | Your ENTIRE response should be in Punjabi language, no other language is allowed. There should be 9 paragraphs. Paragraphs are separated with the markdown divider: *** 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 1 must start with word engineering. There should be 1 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 breakfast. In your response, words with all capital letters should appear less than 32 times. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_51773 | [
{
"content": "Check grammar and clarity:\"In this section, I implemented a real-time handwritten digit classifier by modifying the given python code and running it. This code is shown in Figure 21. As shown in Figure 22, I displayed some digits on screen by opening the pdf file (digit shown in the left side) and I pointed the webcam to the image which the image that capture by the camera is displayed on the right side of the screen. Then, the prediction of the class of the digit is shown in the left side. \" Your answer must contain exactly 6 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 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) Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. In your entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_bullet_lists', 'combination:repeat_prompt', 'detectable_format:number_highlighted_sections', 'punctuation:no_comma'], 'kwargs': [{'num_bullets': 6}, {'prompt_to_repeat': 'Check grammar and clarity:"In this section, I implemented a real-time handwritten digit classifier by modifying the given python code and running it. This code is shown in Figure 21. As shown in Figure 22, I displayed some digits on screen by opening the pdf file (digit shown in the left side) and I pointed the webcam to the image which the image that capture by the camera is displayed on the right side of the screen. Then, the prediction of the class of the digit is shown in the left side. "'}, {'num_highlights': 6}, None]}] | ifeval | multi | Your answer must contain exactly 6 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 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) Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. In your entire response, refrain from the use of any commas. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_23889 | [
{
"content": "You are a novelist, passionately dedicated to creating vivid imagery and immersive stories. In your upcoming crime thriller, the plot revolves around a notorious gang which holds a significant amount of power in the urban landscapes. Your readers are eager to understand the intense and intricate lifestyle within the gang. For the sake of crafting an authentic narrative, portray scenarios where the characters partake in the gang's initiation rituals and frequent activities. Now, whenever the narrative diverges, I'll use the code-word \"Back to the streets\" to refocus the narrative. This task is about challenging your creativity in crafting a crime narrative, so let's produce an engaging story. 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 31 sentences.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_capital', 'detectable_format:constrained_response', 'length_constraints:number_sentences'], 'kwargs': [None, None, {'num_sentences': 31, 'relation': 'less than'}]}] | 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 31 sentences. |
personahub_nujftyxqno1mzynl7qcec2b1 | [
{
"content": "A vintage clothing designer is organizing a 1920s-themed high-tea event and wants to design a seating arrangement that maximizes the unique authentic experience. The event will be held in a circular garden, and the designer plans to set up tables and chairs around a central fountain that is 3 meters in diameter. The designer decides to use round tables, each with a diameter of 1 meter, and each table can accommodate 4 guests around it.\n\n1. Calculate the maximum number of tables that can be placed around the fountain such that each table is touching the next table, while maintaining a walkway of 1 meter between the tables and the outer edge of the circular garden. Assume the radius of the circular garden is 10 meters.\n\n2. To enhance the authenticity of the high-tea experience, vintage teacups are set on each table. Each teacup has a unique design and is placed according to a specific pattern that forms a geometric sequence with the number of teacups per table. If the first table starts with 3 teacups and the total number of teacups across all tables forms a convergent series, find the common ratio of the sequence and calculate the total number of teacups. At the end of your response, please explicitly add a postscript starting with Postscript",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:postscript'], 'kwargs': [{'postscript_marker': 'Postscript'}]}] | ifeval | multi | At the end of your response, please explicitly add a postscript starting with Postscript |
ai2-adapt-dev/numinamath_tir_math_decontaminated_11831 | [
{
"content": "In the middle of a river (the main channel), the water flow speed is 10 km/h, and along the riverbank, the water flow speed is 8 km/h. A boat travels downstream in the middle of the river for 10 hours and covers 360 km. How many hours will it take for the boat to return to its original place along the riverbank? Your response should contain less than 21 sentences. Your answer must contain exactly 6 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_sentences', 'detectable_format:number_bullet_lists', 'combination:two_responses'], 'kwargs': [{'num_sentences': 21, 'relation': 'less than'}, {'num_bullets': 6}, None]}] | ifeval | multi | Your response should contain less than 21 sentences. Your answer must contain exactly 6 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
ai2-adapt-dev/tulu_v3.9_aya_100k_14555 | [
{
"content": "Жанар тоо деген эмне ? Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*. In your response, the letter r should appear less than 11 times. In your response, the word independent should appear at least 3 times. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_lowercase', 'detectable_format:number_highlighted_sections', 'keywords:letter_frequency', 'keywords:frequency', 'combination:two_responses'], 'kwargs': [None, {'num_highlights': 4}, {'letter': 'r', 'let_frequency': 11, 'let_relation': 'less than'}, {'keyword': 'independent', 'frequency': 3, 'relation': 'at least'}, None]}] | ifeval | multi | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*. In your response, the letter r should appear less than 11 times. In your response, the word independent should appear at least 3 times. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
ai2-adapt-dev/tulu_v3.9_aya_100k_38779 | [
{
"content": "Trạng thái nơtron là trạng thái gì ? Đặc điểm của vât chất thuôc trạng thái nơtron là gì? 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 l should appear at least 6 times. Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'keywords:letter_frequency', 'detectable_format:number_highlighted_sections'], 'kwargs': [{'prompt_to_repeat': 'Trạng thái nơtron là trạng thái gì ? Đặc điểm của vât chất thuôc trạng thái nơtron là gì?'}, {'letter': 'l', 'let_frequency': 6, 'let_relation': 'at least'}, {'num_highlights': 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) In your response, the letter l should appear at least 6 times. Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*. |
personahub_0e8bube0luoicikbl00kowkh | [
{
"content": "Write a brief review of two recent art exhibitions in the city. Format your response with exactly three bullet points for each exhibition, detailing the following aspects: the artist's name, the theme of the exhibition, and your overall impression or recommendation. Your response should contain at least 19 sentences. At the end of your response, please explicitly add a postscript starting with P.S At the end of your response, please explicitly add a postscript starting with Postscript: In your response, words with all capital letters should appear at least 36 times. Finish your response with this exact phrase That's my answer.. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_sentences', 'detectable_content:postscript', 'detectable_content:postscript', 'change_case:capital_word_frequency', 'startend:end_checker'], 'kwargs': [{'num_sentences': 19, 'relation': 'at least'}, {'postscript_marker': 'P.S'}, {'postscript_marker': 'Postscript:'}, {'capital_frequency': 36, 'capital_relation': 'at least'}, {'end_phrase': "That's my answer."}]}] | ifeval | multi | Your response should contain at least 19 sentences. At the end of your response, please explicitly add a postscript starting with P.S At the end of your response, please explicitly add a postscript starting with Postscript: In your response, words with all capital letters should appear at least 36 times. Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. |
personahub_k8sox0goi0gblho7uqw5at4g | [
{
"content": "Analyze the current performance of the Mississippi State football team and provide at least 3 pieces of evidence that support their strengths in this season. Answer with at least 3 bullet points in the format below:\n\n* Evidence 1\n* Evidence 2\n* Evidence 3 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 ['kitchen', 'most', 'percentage', 'recommendation'] in the response. In your entire response, refrain from the use of any commas. Your ENTIRE response should be in French language, no other language is allowed. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'keywords:existence', 'punctuation:no_comma', 'language:response_language', 'startend:quotation'], 'kwargs': [None, {'keywords': ['kitchen', 'most', 'percentage', 'recommendation']}, None, {'language': 'fr'}, 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.') Include keywords ['kitchen', 'most', 'percentage', 'recommendation'] in the response. In your entire response, refrain from the use of any commas. Your ENTIRE response should be in French language, no other language is allowed. Wrap your entire response with double quotation marks. |
personahub_0b7hv3mgps8nbv73i6yo8m6s | [
{
"content": "Summarize the main findings of studies on the effectiveness of different coaching techniques in 8 sentences. Each sentence should contain the word 'coaching' at least twice. Repeat the prompt at the end of your 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 ```. Do not include keywords ['account', 'coat', 'lead', 'opportunity'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:title', 'detectable_format:json_format', 'keywords:forbidden_words'], 'kwargs': [None, None, {'forbidden_words': ['account', 'coat', 'lead', 'opportunity']}]}] | ifeval | multi | 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 ```. Do not include keywords ['account', 'coat', 'lead', 'opportunity'] in the response. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_7647 | [
{
"content": "If the asymptote of the hyperbola ${x^2}-\\frac{{y^2}}{{b^2}}=1(b>0)$ is parallel to the line $y=2x-1$, then $b=\\_\\_\\_\\_\\_\\_.$ In your response, the word emphasis should appear at least 1 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency'], 'kwargs': [{'keyword': 'emphasis', 'frequency': 1, 'relation': 'at least'}]}] | ifeval | multi | In your response, the word emphasis should appear at least 1 times. |
personahub_ajx0n0es2hq6ql98qxc9d51r | [
{
"content": "The CEO of a large corporation believes that time spent reading fantasy novels is unproductive and could be better spent on activities that directly contribute to the company's bottom line. The CEO estimates that each hour spent on such novels results in a 2% decrease in productivity for the day. If employees collectively spend \\( x \\) hours per day reading fantasy novels, the company's daily productivity can be modeled by the polynomial function \\( P(x) = -0.02x^3 + 1.5x^2 + 100 \\), where \\( P(x) \\) represents the productivity index in percentage. \n\n1. Determine the number of hours \\( x \\) that the employees can spend reading without causing the productivity index to drop below 95%. Solve the inequality \\( -0.02x^3 + 1.5x^2 + 100 \\geq 95 \\).\n\n2. The CEO wants to offer a productivity bonus that compensates for the lost productivity if employees choose to read for 3 hours a day. Calculate the amount of productivity (in percentage points) that needs to be compensated if employees read for 3 hours. In your response, the word commercial should appear at least 4 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency'], 'kwargs': [{'keyword': 'commercial', 'frequency': 4, 'relation': 'at least'}]}] | ifeval | multi | In your response, the word commercial should appear at least 4 times. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_51547 | [
{
"content": "In the expansion of $(x+y)^{2}(x-2y)^{4}$, the coefficient of $x^{2}y^{4}$ is ( ).\n\nA: $88$\n\nB: $104$\n\nC: $-40$\n\nD: $-24$ Answer with less than 414 words. In your response, words with all capital letters should appear at least 3 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)",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words', 'change_case:capital_word_frequency', 'combination:repeat_prompt'], 'kwargs': [{'num_words': 414, 'relation': 'less than'}, {'capital_frequency': 3, 'capital_relation': 'at least'}, {'prompt_to_repeat': 'In the expansion of $(x+y)^{2}(x-2y)^{4}$, the coefficient of $x^{2}y^{4}$ is ( ).\n\nA: $88$\n\nB: $104$\n\nC: $-40$\n\nD: $-24$'}]}] | ifeval | multi | Answer with less than 414 words. In your response, words with all capital letters should appear at least 3 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) |
personas_math_easy_0l2x4cavgxwbgqihl1bu1zuh | [
{
"content": "A rare book collector has a collection of 120 rare books and cherishes the peaceful melodies that fill their shared home. They decide to display their books in a room where they can also listen to music. They plan to have 4 equal shelves for the books. However, they recently acquired 8 more rare books from an auction. How many books will they place on each shelf after adding the new books to their collection? The response must contain at least 1 placeholders represented by square brackets, such as [address]. The response must contain at least 2 placeholders represented by square brackets, such as [address].",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:number_placeholders', 'detectable_content:number_placeholders'], 'kwargs': [{'num_placeholders': 1}, {'num_placeholders': 2}]}] | ifeval | multi | The response must contain at least 1 placeholders represented by square brackets, such as [address]. The response must contain at least 2 placeholders represented by square brackets, such as [address]. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_56286 | [
{
"content": "Random popular ocean scene, one word with rose buds before it Your answer must contain exactly 6 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. The response must contain at least 2 placeholders represented by square brackets, such as [address].",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_bullet_lists', 'change_case:english_lowercase', 'change_case:english_lowercase', 'detectable_content:number_placeholders'], 'kwargs': [{'num_bullets': 6}, None, None, {'num_placeholders': 2}]}] | ifeval | multi | Your answer must contain exactly 6 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. The response must contain at least 2 placeholders represented by square brackets, such as [address]. |
ai2-adapt-dev/flan_v2_converted_48749 | [
{
"content": "Which of these sentences doesn't make sense?\nOptions:\n- Sentence A: \"A video recorder can be used to tape television show\"\n- Sentence B: \"A comb can be used to tape television show.\"\n Let me think hard. Detailed solution: Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. In your response, the word scale should appear less than 3 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.') In your response, words with all capital letters should appear at least 34 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.')",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:json_format', 'keywords:frequency', 'detectable_format:constrained_response', 'change_case:capital_word_frequency', 'detectable_format:constrained_response'], 'kwargs': [None, {'keyword': 'scale', 'frequency': 3, 'relation': 'less than'}, None, {'capital_frequency': 34, 'capital_relation': 'at least'}, None]}] | ifeval | multi | Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. In your response, the word scale should appear less than 3 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.') In your response, words with all capital letters should appear at least 34 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.') |
personas_math_easy_fydmv1mtvk9htt3ytsz0puf8 | [
{
"content": "A geologist with over 15 years of experience in the oil drilling industry is analyzing two drilling sites. At the first site, the geologist estimates that they can extract 350 barrels of oil per day. At the second site, the estimate is 275 barrels per day. The geologist plans to operate the first site for 12 days and the second site for 15 days. How many total barrels of oil does the geologist expect to extract from both sites combined during these periods? In your response, words with all capital letters should appear at least 33 times. 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 3 must start with word skin. Your response must have 5 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 entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:capital_word_frequency', 'length_constraints:nth_paragraph_first_word', 'detectable_format:multiple_sections', 'punctuation:no_comma'], 'kwargs': [{'capital_frequency': 33, 'capital_relation': 'at least'}, {'num_paragraphs': 4, 'nth_paragraph': 3, 'first_word': 'skin'}, {'section_spliter': 'Section', 'num_sections': 5}, None]}] | ifeval | multi | In your response, words with all capital letters should appear at least 33 times. 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 3 must start with word skin. Your response must have 5 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 entire response, refrain from the use of any commas. |
personahub_3fb43hkkix9w5qjh8z6j6i3p | [
{
"content": "A former Second Life user, Alex, once invested significant time and virtual currency in the game, only to face a substantial devaluation of their virtual assets. Initially, Alex acquired 10,000 Linden Dollars (the virtual currency in Second Life) by exchanging $40 USD at a rate of 250 Linden Dollars per 1 USD.\n\n1. Due to negative experiences, Alex decided to withdraw from Second Life entirely. However, the value of the Linden Dollar had depreciated, and the new exchange rate was 400 Linden Dollars per 1 USD. Calculate the monetary loss or gain (in USD) Alex incurred when they exchanged their remaining 10,000 Linden Dollars back to USD at the new exchange rate.\n\n2. To mitigate the loss and invest in real-world skills, Alex decided to enroll in an online course, which costs $15 per month. If Alex plans to use only the funds from the Linden Dollar exchange to pay for the course, determine the maximum number of full months Alex can afford the course without any additional funds. 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>>. 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 8 must start with word airline. Your ENTIRE response should be in Vietnamese language, no other language is allowed. In your response, the word candle should appear at least 3 times.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'detectable_format:title', 'length_constraints:nth_paragraph_first_word', 'language:response_language', 'keywords:frequency'], 'kwargs': [None, None, {'num_paragraphs': 8, 'nth_paragraph': 8, 'first_word': 'airline'}, {'language': 'vi'}, {'keyword': 'candle', 'frequency': 3, 'relation': 'at least'}]}] | 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>>. 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 8 must start with word airline. Your ENTIRE response should be in Vietnamese language, no other language is allowed. In your response, the word candle should appear at least 3 times. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_9797 | [
{
"content": "How can I eradicate weeds in my garden without using harmful chemicals? In your response, words with all capital letters should appear less than 23 times.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:capital_word_frequency'], 'kwargs': [{'capital_frequency': 23, 'capital_relation': 'less than'}]}] | ifeval | multi | In your response, words with all capital letters should appear less than 23 times. |
personahub_nyz4ygpx7qg18dw0lmdwg4jz | [
{
"content": "A filmmaker is working on a project about mental health and aims to shed light on patients' experiences. To accomplish this, the filmmaker decides to use a combination of statistical analysis and network theory to understand the relationships between various mental health symptoms and their impacts on patients' lives. \n\nThe filmmaker collects data from 150 patients, each reporting the severity of 10 different symptoms on a scale from 0 to 10. Let \\( S_{ij} \\) represent the severity score of symptom \\( j \\) for patient \\( i \\).\n\n1. **Principal Component Analysis (PCA):** Perform PCA on the dataset of symptom severity scores to reduce the dimensionality. Compute the eigenvalues of the covariance matrix of the dataset. Identify the number of principal components needed to explain at least 85% of the total variance.\n\n2. **Network Analysis:** Construct a weighted, undirected graph where each node represents a symptom, and the weight of each edge between nodes \\( A \\) and \\( B \\) is given by the Pearson correlation coefficient of the severity scores of symptoms \\( A \\) and \\( B \\) across all patients. Determine the adjacency matrix of this graph and identify the connected components. How many connected components are there, and which symptoms belong to the largest connected component?\n\nNote: Assume you have access to all necessary computational tools to perform PCA and network analysis. 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) Include keywords ['cell', 'convert', 'listen', 'register'] in the response. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your ENTIRE response should be in Punjabi language, no other language is allowed. Finish your response with this exact phrase The END.. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'keywords:existence', 'detectable_format:json_format', 'language:response_language', 'startend:end_checker'], 'kwargs': [{'prompt_to_repeat': "A filmmaker is working on a project about mental health and aims to shed light on patients' experiences. To accomplish this, the filmmaker decides to use a combination of statistical analysis and network theory to understand the relationships between various mental health symptoms and their impacts on patients' lives. \n\nThe filmmaker collects data from 150 patients, each reporting the severity of 10 different symptoms on a scale from 0 to 10. Let \\( S_{ij} \\) represent the severity score of symptom \\( j \\) for patient \\( i \\).\n\n1. **Principal Component Analysis (PCA):** Perform PCA on the dataset of symptom severity scores to reduce the dimensionality. Compute the eigenvalues of the covariance matrix of the dataset. Identify the number of principal components needed to explain at least 85% of the total variance.\n\n2. **Network Analysis:** Construct a weighted, undirected graph where each node represents a symptom, and the weight of each edge between nodes \\( A \\) and \\( B \\) is given by the Pearson correlation coefficient of the severity scores of symptoms \\( A \\) and \\( B \\) across all patients. Determine the adjacency matrix of this graph and identify the connected components. How many connected components are there, and which symptoms belong to the largest connected component?\n\nNote: Assume you have access to all necessary computational tools to perform PCA and network analysis."}, {'keywords': ['cell', 'convert', 'listen', 'register']}, None, {'language': 'pa'}, {'end_phrase': 'The END.'}]}] | 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) Include keywords ['cell', 'convert', 'listen', 'register'] in the response. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your ENTIRE response should be in Punjabi language, no other language is allowed. Finish your response with this exact phrase The END.. No other words should follow this phrase. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_28734 | [
{
"content": "What's the logic behind disallowing laptops from getting scholarships? 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. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:title', 'change_case:english_capital', 'detectable_format:number_highlighted_sections'], 'kwargs': [None, None, {'num_highlights': 3}]}] | ifeval | multi | 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. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_30927 | [
{
"content": "Can you guide me in giving this SVG a sketched or hand-drawn effect?\n<svg width=\"32\" height=\"32\" viewBox=\"0 0 32 32\" fill=\"none\" xmlns=\"http://www.w3.org/2000/svg\">\n<path d=\"M26.5 12.67C26.5 13.58 26.28 14.44 25.9 15.2C27.16 16.14 28 17.63 28 19.32C28 22.16 25.68 24.48 22.84 24.48H19V31.02H13V24.48H10.16C7.32 24.48 5 22.16 5 19.32C5 17.63 5.84 16.14 7.1 15.2C6.72 14.44 6.5 13.58 6.5 12.67C6.5 9.76 8.68 7.37 11.5 7.04V7C11.5 4.24 13.74 2 16.5 2C19.26 2 21.5 4.24 21.5 7V7.04C24.31 7.37 26.5 9.76 26.5 12.67ZM15 24.48V29.02H17V24.48H15Z\" fill=\"#212121\"/>\n</svg>\n 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.') Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. 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 1 must start with word kitchen.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'detectable_format:json_format', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [None, None, {'num_paragraphs': 3, 'nth_paragraph': 1, 'first_word': 'kitchen'}]}] | 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.') Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. 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 1 must start with word kitchen. |
personahub_ihob2bnbgadtu0xlke20p8vk | [
{
"content": "Write a 500-word article that explains the importance of biodiversity conservation and its impact on climate change. Use simple language to make it accessible for a general audience. Include a title for the article wrapped in double angular brackets, i.e. <<title>>, and ensure that each paragraph starts with a capitalized word. Format the article in one of the following styles: narrative, informative, or persuasive. In your response, words with all capital letters should appear at least 40 times. In your response, the word individual should appear at least 6 times. 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 2 must start with word reflection. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:capital_word_frequency', 'keywords:frequency', 'length_constraints:nth_paragraph_first_word', 'startend:quotation'], 'kwargs': [{'capital_frequency': 40, 'capital_relation': 'at least'}, {'keyword': 'individual', 'frequency': 6, 'relation': 'at least'}, {'num_paragraphs': 3, 'nth_paragraph': 2, 'first_word': 'reflection'}, None]}] | ifeval | multi | In your response, words with all capital letters should appear at least 40 times. In your response, the word individual should appear at least 6 times. 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 2 must start with word reflection. Wrap your entire response with double quotation marks. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_6515 | [
{
"content": "tell me a story of a gay couple and what they do the first night after marriage. 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.') Do not include keywords ['image', 'lie', 'source', 'war'] in the response. 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 Include keywords ['animal', 'peak', 'replacement', 'tradition'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'detectable_format:constrained_response', 'keywords:forbidden_words', 'detectable_format:number_bullet_lists', 'keywords:existence'], 'kwargs': [None, None, {'forbidden_words': ['image', 'lie', 'source', 'war']}, {'num_bullets': 2}, {'keywords': ['animal', 'peak', 'replacement', 'tradition']}]}] | 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.') Do not include keywords ['image', 'lie', 'source', 'war'] in the response. Your answer must contain exactly 2 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Include keywords ['animal', 'peak', 'replacement', 'tradition'] in the response. |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_9827 | [
{
"content": "Samantha's book signing event was 3 times as large as Emily's art exhibition. If a total of 180 people attended both events, how many people were at Samantha's book signing event? In your response, words with all capital letters should appear less than 10 times. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:capital_word_frequency', 'startend:quotation'], 'kwargs': [{'capital_frequency': 10, 'capital_relation': 'less than'}, None]}] | ifeval | multi | In your response, words with all capital letters should appear less than 10 times. Wrap your entire response with double quotation marks. |
personahub_p47mj2mrfiprygjuk2ssdkm3 | [
{
"content": "A popular TV show host, known for demanding top-notch broadcasting services, is preparing for a special live show. The show requires a high-speed internet connection with a guaranteed minimum bandwidth to ensure uninterrupted streaming. The host's technical team has determined that the live show will generate data at a rate that follows a sinusoidal function due to the fluctuating nature of live interactions and multimedia content.\n\n1. The data rate \\( D(t) \\) in megabits per second (Mbps) at time \\( t \\) minutes during the live show is modeled by the function \\( D(t) = 100 + 50\\sin\\left(\\frac{\\pi t}{15}\\right) \\). Calculate the total amount of data (in megabits) transmitted during the first 30 minutes of the live show.\n\n2. To ensure the quality of the live broadcast, the internet connection must have a bandwidth that is at least 10% greater than the maximum data rate observed during the show. Determine the minimum required bandwidth (in Mbps) for the internet connection. Wrap your entire response with double quotation marks. At the end of your response, please explicitly add a postscript starting with Postscript Include keywords ['bunch', 'conflict', 'control', 'train'] in the response. Include keywords ['nobody', 'pitch', 'roof', 'touch'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['startend:quotation', 'detectable_content:postscript', 'keywords:existence', 'keywords:existence'], 'kwargs': [None, {'postscript_marker': 'Postscript'}, {'keywords': ['bunch', 'conflict', 'control', 'train']}, {'keywords': ['nobody', 'pitch', 'roof', 'touch']}]}] | ifeval | multi | Wrap your entire response with double quotation marks. At the end of your response, please explicitly add a postscript starting with Postscript Include keywords ['bunch', 'conflict', 'control', 'train'] in the response. Include keywords ['nobody', 'pitch', 'roof', 'touch'] in the response. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_13951 | [
{
"content": "How can I blow away the judges with my presentation skills? There should be 1 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_paragraphs'], 'kwargs': [{'num_paragraphs': 1}]}] | ifeval | multi | There should be 1 paragraphs. Paragraphs are separated with the markdown divider: *** |
science.bioasq_general_qa.331 | [
{
"content": "You will be shown a question, followed by excerpts from biomedical research papers. Please answer the question based on the provided context. Do not include any text in your response other than the answer.\n\nQuestion: What is the role of brain natriuretic peptide in traumatic brain injury patients ?\n\nContext: This study provides evidence that BNP plasma concentrations increase rapidly after TBI. Plasma BNP concentrations are correlated with hyponatremia in severe TBI patients but not in mild and moderate TBI patients. Furthermore, patients with elevated ICP have a higher serum BNP level in first 4 days after injury.\nIn average, the peak of BNP level was measured at 703.9 pg/mL±179.1 pg/mL on day 3 after injury, which was correlated to the severity of TBI. Among patients with severe TBI, plasma NT-proBNP concentrations in patients with hyponatremia were statistically higher than those without hyponatremia (p<0.05). In the hyponatremic group, the plasma NT-proBNP increased to a peak of 1001.16 pg/mL±131.52 pg/mL within 48 hours after injury and maintained at a high level for 3 days. In the normonatremic group, the plasma NT-proBNP reached a peak of 826.43 pg/mL±337.43 pg/mL on day 5 and quickly decreased thereafter. In addition, we found plasma NT-proBNP concentrations in patients with ICP>15 mm Hg were significantly higher than those in patients with ICP≤15 mm Hg (p<0.01).\nThere is emerging evidence to suggest that brain natriuretic peptide (BNP) is elevated after acute brain injury, and that it may play an adaptive role in recovery through augmentation of cerebral blood flow (CBF).\nhBNP improves neurological function in murine models of TBI and ICH, and was associated with enhanced CBF and downregulation of neuroinflammatory responses. hBNP may represent a novel therapeutic strategy after acute CNS injury.\nHere, we describe 2 cases of CSW in TBI patients with elevated BNP levels.\nThese patients with TBI had findings consistent with CSW with elevated BNP levels in the setting of normal cardiac function.\nWe measured NT-proBNP levels in cerebrospinal fluid (CSF) and serum of 14 patients suffering from severe TBI (GCS15 mm Hg (n=6), the serum (800+/-150 pg/mL) and CSF levels (55+/-9 pg/mL) of NT-proBNP were significantly increased after 24 h, as compared to patients with ICP15 mm Hg.\nBNP plasma concentrations are elevated shortly after head injury and are continuously elevated during the acute phase in patients with more extensive SAH and in those with elevated ICP, and correlate with poor outcomes.\nBACKGROUND: According to the literature, serum beta-natriuretic peptide (BNP) levels have been shown to increase in adult trauma patients, specifically for those with traumatic brain injury and in those with intracranial hemorrhage. In your response, the letter j should appear less than 12 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency'], 'kwargs': [{'letter': 'j', 'let_frequency': 12, 'let_relation': 'less than'}]}] | ifeval | multi | In your response, the letter j should appear less than 12 times. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_33705 | [
{
"content": "The 31st Universiade, \"Chengdu Achieves Dreams,\" will open on June 26, 2022. A souvenir of the Universiade named \"Rong Bao,\" with a cost of 30 yuan, has been put on the market for trial sales by merchants. According to market research, the daily sales volume $y$ (pieces) is a linear function of the selling price $x$ (33 ≤ x ≤ 58, and x is a positive integer) of each item. Some corresponding data is shown in the table below:\n\n| Selling Price $x$ (yuan) | ... | 35 | 36 | 37 | 38 | ... |\n|--------------------------|-----|----|----|----|----|-----|\n| Daily Sales Volume $y$ (pieces) | ... | 90 | 88 | 86 | 84 | ... |\n\n$(1)$ Write down the functional relationship between $y$ and $x$ directly.\n\n$(2)$ Find the selling price per item when the merchant earns 800 yuan per day.\n\n$(3)$ Determine the selling price of the souvenir when the merchant maximizes the profit obtained from selling the souvenir each day. What is the maximum profit? Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker', 'startend:end_checker', 'combination:two_responses', 'combination:two_responses'], 'kwargs': [{'end_phrase': 'Any other questions?'}, {'end_phrase': 'Any other questions?'}, None, None]}] | ifeval | multi | Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
personahub_roqovq8ebz06q4gdegvezlbu | [
{
"content": "A web developer has been working on a project for a client who can attest to their reliability and professionalism. The client has a complex website that receives an average of 5,000 unique visitors per day. The website's performance is measured by the average load time per page, and the client wants to ensure that the load time remains optimal even as traffic increases.\n\n1. Suppose the load time \\( L(t) \\) in seconds can be modeled by the function \\( L(t) = \\frac{a}{\\sqrt{t}} + bt \\), where \\( t \\) is the time in days since the website launch, and \\( a \\) and \\( b \\) are constants. Given that the initial load time at \\( t = 1 \\) day is 2 seconds and after 4 days the load time has increased to 3 seconds, determine the constants \\( a \\) and \\( b \\).\n\n2. The client predicts that the traffic will increase exponentially and can be modeled by the function \\( V(t) = 5000 \\cdot e^{kt} \\), where \\( k \\) is a constant growth rate. If the traffic is expected to double in 10 days, calculate the constant \\( k \\). Then, using the determined values of \\( a \\) and \\( b \\) from the first sub-problem, find the load time \\( L(t) \\) at \\( t = 10 \\) days.\n\nNote: \\( e \\) is the base of the natural logarithm. There should be 1 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_paragraphs'], 'kwargs': [{'num_paragraphs': 1}]}] | ifeval | multi | There should be 1 paragraphs. Paragraphs are separated with the markdown divider: *** |
personahub_nft3f0h5cdovg0d284l2momf | [
{
"content": "As a talented chef, you decide to create a special pastry for skiers that consists of a flaky crust and a rich chocolate filling. You determine that the amount of chocolate filling needed is dependent on the number of pastries made, following the equation \\( f(x) = 4x^2 + 12x + 9 \\), where \\( x \\) is the number of pastries produced and \\( f(x) \\) is the amount of chocolate in ounces required. \n\n1. If you have a total of 225 ounces of chocolate available, how many pastries can you make? Set up and solve the quadratic equation to find the possible values of \\( x \\).\n\n2. After a successful day on the slopes, you find that the skiers particularly love your pastries. You decide to adjust the recipe slightly by increasing the chocolate filling by 2 ounces per pastry. Revise the equation to reflect this change and determine the new maximum number of pastries you can make with the same 225 ounces of chocolate. Your answer must contain exactly 7 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': 7}]}] | ifeval | multi | Your answer must contain exactly 7 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 |
personahub_z8pskqouombr44xkib6h3rss | [
{
"content": "A patient home health aide is assisting an elderly woman who has a rich history of life experiences spanning a century. The woman was born in 1923 and has lived through numerous historical events that she fondly recounts. The aide is fascinated by the stories and decides to model the woman's cumulative number of significant life events based on her age using a function that reflects her unique life journey.\n\n1. Let's define a function \\( f(t) \\), where \\( t \\) represents the woman's age, and \\( f(t) \\) represents the estimated cumulative number of significant life events she has experienced by age \\( t \\). Suppose the function can be modeled by the differential equation:\n\n \\[\n \\frac{df}{dt} = \\alpha \\cdot (100 - t) \\cdot e^{-\\beta t}\n \\]\n\n where \\( \\alpha \\) and \\( \\beta \\) are constants. Given that \\( f(0) = 0 \\) and \\( f(100) = 150 \\), determine the values of \\( \\alpha \\) and \\( \\beta \\).\n\n2. The aide is curious about how the rate of change in significant life events compares to the average number of stories the woman tells per year, which is modeled as a constant \\( s \\). If the average number of stories is 1.5 times the rate of change of events at age 75, find the value of \\( s \\) in terms of \\( \\alpha \\) and \\( \\beta \\). Your ENTIRE response should be in Spanish language, no other language is allowed. Your response must have 10 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] 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) At the end of your response, please explicitly add a postscript starting with P.P.S",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language', 'detectable_format:multiple_sections', 'combination:repeat_prompt', 'detectable_content:postscript'], 'kwargs': [{'language': 'es'}, {'section_spliter': 'Paragraph', 'num_sections': 10}, {'prompt_to_repeat': "A patient home health aide is assisting an elderly woman who has a rich history of life experiences spanning a century. The woman was born in 1923 and has lived through numerous historical events that she fondly recounts. The aide is fascinated by the stories and decides to model the woman's cumulative number of significant life events based on her age using a function that reflects her unique life journey.\n\n1. Let's define a function \\( f(t) \\), where \\( t \\) represents the woman's age, and \\( f(t) \\) represents the estimated cumulative number of significant life events she has experienced by age \\( t \\). Suppose the function can be modeled by the differential equation:\n\n \\[\n \\frac{df}{dt} = \\alpha \\cdot (100 - t) \\cdot e^{-\\beta t}\n \\]\n\n where \\( \\alpha \\) and \\( \\beta \\) are constants. Given that \\( f(0) = 0 \\) and \\( f(100) = 150 \\), determine the values of \\( \\alpha \\) and \\( \\beta \\).\n\n2. The aide is curious about how the rate of change in significant life events compares to the average number of stories the woman tells per year, which is modeled as a constant \\( s \\). If the average number of stories is 1.5 times the rate of change of events at age 75, find the value of \\( s \\) in terms of \\( \\alpha \\) and \\( \\beta \\)."}, {'postscript_marker': 'P.P.S'}]}] | ifeval | multi | Your ENTIRE response should be in Spanish language, no other language is allowed. Your response must have 10 sections. Mark the beginning of each section with Paragraph X, such as:
Paragraph 1
[content of section 1]
Paragraph 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) At the end of your response, please explicitly add a postscript starting with P.P.S |
personas_math_easy_gj6dhxfwmpwmxuj4zfnpagfi | [
{
"content": "Dr. Smith is a criminal psychologist focusing on the impact of sex crimes on victims. She is conducting a study on the recovery progress of 6 victims over the course of a year. Each victim attends weekly therapy sessions. The number of sessions each victim attends in a year is as follows:\n\n1. Victim A attends 48 sessions.\n2. Victim B attends 52 sessions.\n3. Victim C attends 50 sessions.\n4. Victim D attends 45 sessions.\n5. Victim E attends 47 sessions.\n6. Victim F attends 49 sessions.\n\nDr. Smith wants to calculate the average number of therapy sessions attended per victim over the year. What is the average number of sessions attended by the victims? Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
]
| [{'instruction_id': ['combination:two_responses'], 'kwargs': [None]}] | ifeval | multi | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
ai2-adapt-dev/tulu_v3.9_aya_100k_94487 | [
{
"content": "مما خلق الله تعالى الجان ؟\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",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_bullet_lists'], 'kwargs': [{'num_bullets': 10}]}] | 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 |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_51828 | [
{
"content": "напиши более подробно Фонд оплаты труда также может быть представлен в четырех формах:\n1. Часовой - включает оплату по тарифным ставкам, окладам и сдельным расценкам за фактически отработанные человеко-часы, а также доплаты мастерам за руководство учениками и компенсации за отклонения от нормальных условий труда;\n2. Дневной - охватывает фонд часовой оплаты труда и часы, которые не были отработаны, но подлежат оплате по закону, то есть за фактически отработанные человеко-дни, включая доплаты за сверхурочные работы;\n3. Месячный - включает все составляющие фонда дневной заработной платы, а также оплату очередных и дополнительных отпусков, выплаты за неотработанное время, единовременные и поощрительные средства, а также компенсации на питание, жилье и топливо;\n4. Годовой - является суммой всех месячных фондов оплаты труда. In your response, the letter v should appear at least 1 times. 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 1 must start with word drunk.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [{'letter': 'v', 'let_frequency': 1, 'let_relation': 'at least'}, {'num_paragraphs': 6, 'nth_paragraph': 1, 'first_word': 'drunk'}]}] | ifeval | multi | In your response, the letter v should appear at least 1 times. 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 1 must start with word drunk. |
ai2-adapt-dev/flan_v2_converted_51605 | [
{
"content": "Ques: Yes / no, is the following a verifiable fact?\n\"Disgust coincides with morals and emotions.\"\nAns: I'm thinking hard. So here's my take: Disgust is an emotion that deals with morality. The answer is yes.\n---\nQues: Does the following sentence make sense?\n\"If viewed from space you will see that the United States Numbered Highway System is an elaborate symbol that can only be read by extraterrestrials.\"\nOptions:\n- yes\n- no\nAns: I'm thinking hard. So here's my take: No work was put into the asthetics of the US Highway system and it was not meant in anyway for ET. The answer is no.\n---\nQues: Does the following sentence make sense?\n\"One can listen to Johnny Cash on youtube.\"\nOptions:\n- yes\n- no\nAns: Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. Your response must have 1 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': ['startend:end_checker', 'detectable_format:multiple_sections'], 'kwargs': [{'end_phrase': "That's my answer."}, {'section_spliter': 'Sec.', 'num_sections': 1}]}] | ifeval | multi | Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. Your response must have 1 sections. Mark the beginning of each section with Sec. X, such as:
Sec. 1
[content of section 1]
Sec. 2
[content of section 2] |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_19209 | [
{
"content": "Alexis is going for a bike ride. She rides uphill at 8 MPH and downhill at 12 MPH. The trail is 9 miles long, with 40% of it being uphill and the rest downhill. How long does it take her to complete the ride in minutes? Do not include keywords ['delay', 'double', 'joint', 'office'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:forbidden_words'], 'kwargs': [{'forbidden_words': ['delay', 'double', 'joint', 'office']}]}] | ifeval | multi | Do not include keywords ['delay', 'double', 'joint', 'office'] in the response. |
personahub_wyxahf3521jugss8ilihuuog | [
{
"content": "Coach Ricardo is preparing his Brazilian national volleyball team for an upcoming international tournament. He has a unique coaching method where he evaluates the performance of his team based on complex statistical models and pattern recognition.\n\n1. **Statistical Analysis Sub-problem**: Coach Ricardo uses a multivariate regression model to predict the probability \\( P \\) of his team winning a match. The model considers three factors: attack efficiency ( \\( A \\) ), defense efficiency ( \\( D \\) ), and team synergy ( \\( S \\) ). The relationship is given by:\n\n\\[ P = \\frac{1}{1 + e^{-(\\beta_0 + \\beta_1 A + \\beta_2 D + \\beta_3 S)}} \\]\n\nGiven that the coefficients are \\( \\beta_0 = -0.5 \\), \\( \\beta_1 = 2.3 \\), \\( \\beta_2 = 1.8 \\), and \\( \\beta_3 = 1.1 \\), calculate the probability \\( P \\) if the attack efficiency \\( A \\) is 0.7, the defense efficiency \\( D \\) is 0.6, and the team synergy \\( S \\) is 0.8.\n\n2. **Pattern Recognition Sub-problem**: To further refine his strategy, Coach Ricardo analyzes the passing patterns of his team using network theory. The passing network is represented by an adjacency matrix \\( \\mathbf{M} \\) where \\( M_{ij} \\) indicates the number of successful passes from player \\( i \\) to player \\( j \\). The matrix \\( \\mathbf{M} \\) for a particular match is given by:\n\n\\[ \\mathbf{M} = \\begin{pmatrix}\n0 & 5 & 3 & 2 & 1 \\\\\n4 & 0 & 6 & 1 & 3 \\\\\n2 & 7 & 0 & 4 & 5 \\\\\n3 & 1 & 2 & 0 & 6 \\\\\n5 & 3 & 4 & 2 & 0 \n\\end{pmatrix} \\]\n\nDetermine the eigenvalues of the matrix \\( \\mathbf{M} \\). Your ENTIRE response should be in Korean language, no other language is allowed. Your response must have 10 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] 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 1 must start with word convert. Your response should contain at least 31 sentences. 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', 'detectable_format:multiple_sections', 'length_constraints:nth_paragraph_first_word', 'length_constraints:number_sentences', 'combination:repeat_prompt'], 'kwargs': [{'language': 'ko'}, {'section_spliter': 'Paragraph', 'num_sections': 10}, {'num_paragraphs': 6, 'nth_paragraph': 1, 'first_word': 'convert'}, {'num_sentences': 31, 'relation': 'at least'}, {'prompt_to_repeat': 'Coach Ricardo is preparing his Brazilian national volleyball team for an upcoming international tournament. He has a unique coaching method where he evaluates the performance of his team based on complex statistical models and pattern recognition.\n\n1. **Statistical Analysis Sub-problem**: Coach Ricardo uses a multivariate regression model to predict the probability \\( P \\) of his team winning a match. The model considers three factors: attack efficiency ( \\( A \\) ), defense efficiency ( \\( D \\) ), and team synergy ( \\( S \\) ). The relationship is given by:\n\n\\[ P = \\frac{1}{1 + e^{-(\\beta_0 + \\beta_1 A + \\beta_2 D + \\beta_3 S)}} \\]\n\nGiven that the coefficients are \\( \\beta_0 = -0.5 \\), \\( \\beta_1 = 2.3 \\), \\( \\beta_2 = 1.8 \\), and \\( \\beta_3 = 1.1 \\), calculate the probability \\( P \\) if the attack efficiency \\( A \\) is 0.7, the defense efficiency \\( D \\) is 0.6, and the team synergy \\( S \\) is 0.8.\n\n2. **Pattern Recognition Sub-problem**: To further refine his strategy, Coach Ricardo analyzes the passing patterns of his team using network theory. The passing network is represented by an adjacency matrix \\( \\mathbf{M} \\) where \\( M_{ij} \\) indicates the number of successful passes from player \\( i \\) to player \\( j \\). The matrix \\( \\mathbf{M} \\) for a particular match is given by:\n\n\\[ \\mathbf{M} = \\begin{pmatrix}\n0 & 5 & 3 & 2 & 1 \\\\\n4 & 0 & 6 & 1 & 3 \\\\\n2 & 7 & 0 & 4 & 5 \\\\\n3 & 1 & 2 & 0 & 6 \\\\\n5 & 3 & 4 & 2 & 0 \n\\end{pmatrix} \\]\n\nDetermine the eigenvalues of the matrix \\( \\mathbf{M} \\).'}]}] | ifeval | multi | Your ENTIRE response should be in Korean language, no other language is allowed. Your response must have 10 sections. Mark the beginning of each section with Paragraph X, such as:
Paragraph 1
[content of section 1]
Paragraph 2
[content of section 2] 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 1 must start with word convert. Your response should contain at least 31 sentences. 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/evol_codealpaca_heval_decontaminated_25867 | [
{
"content": "Edit the following Python program to make a correct API request and parse the response.\nimport requests\n\nurl = 'https://api.example.com/users'\n\nresponse = requests.get(url)\n\nprint(response.json()) 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 entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'punctuation:no_comma'], 'kwargs': [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 entire response, refrain from the use of any commas. |
ai2-adapt-dev/flan_v2_converted_28079 | [
{
"content": "You are given a sentence in English. Your job is to translate the English sentence into Portugese.\n\nExample Input: Steaming ought to be faster.\nExample Output: Cozinhar a vapor deveria ser mais rápido.\n\nExample Input: Our state test scores have gone up more than 80 points since we've become our own school.\nExample Output: Os nossos resultados, nos exames estatais, subiram mais de 80 pontos, desde que nos tornámos na nossa própria escola.\n\nExample Input: That's the part that works.\nExample Output: The response must contain at least 8 placeholders represented by square brackets, such as [address].",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:number_placeholders'], 'kwargs': [{'num_placeholders': 8}]}] | ifeval | multi | The response must contain at least 8 placeholders represented by square brackets, such as [address]. |
ai2-adapt-dev/tulu_v3.9_aya_100k_95317 | [
{
"content": "Giải thích ý nghĩa từ “tràm chim”? 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'], 'kwargs': [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.') |
personahub_g1h3zmpgk62ubvxjtcqtcb0l | [
{
"content": "An enthusiastic education graduate is tasked with designing a new curriculum module for an advanced mathematics course. As part of the curriculum, they want to incorporate a challenging problem related to the implementation and evolution of mathematical models over time.\n\n1. The graduate decides to focus on a discrete-time dynamical system that models the effectiveness \\( E(t) \\) of a curriculum over time \\( t \\). The effectiveness is modeled by the non-linear recurrence relation:\n \\[\n E(t+1) = E(t) + rE(t)(1 - \\frac{E(t)}{K}) - cE(t),\n \\]\n where \\( r \\) is the growth rate, \\( K \\) is the carrying capacity, and \\( c \\) is a constant representing curriculum fatigue. Given that \\( r = 0.1 \\), \\( K = 100 \\), \\( c = 0.02 \\), and the initial effectiveness \\( E(0) = 10 \\), determine the long-term behavior of \\( E(t) \\). Is there a stable equilibrium, and if so, what is its value?\n\n2. To further evaluate the success of the curriculum, the graduate includes a continuous-time model for the cumulative knowledge \\( N(t) \\) acquired by students, described by the differential equation:\n \\[\n \\frac{dN}{dt} = \\alpha E(t) - \\beta N(t),\n \\]\n where \\( \\alpha \\) is the rate of knowledge acquisition proportional to the effectiveness \\( E(t) \\), and \\( \\beta \\) is the forgetting rate. Assuming \\( \\alpha = 0.5 \\) and \\( \\beta = 0.1 \\), and using the long-term behavior of \\( E(t) \\) from the previous sub-problem, solve for the steady-state solution of \\( N(t) \\). There should be 9 paragraphs. Paragraphs are separated with the markdown divider: *** 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_paragraphs', 'detectable_format:constrained_response'], 'kwargs': [{'num_paragraphs': 9}, None]}] | ifeval | multi | There should be 9 paragraphs. Paragraphs are separated with the markdown divider: *** 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_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_18435 | [
{
"content": "Greetings, my friend! I'm working on a creative writing project that requires me to come up with a captivating story about a daring individual who manages to infiltrate a prestigious organization to uncover some secrets. I'm trying to incorporate a hint of international flair, and I'm considering using a mix of English and a bit of French to add to the intrigue. Here's a rough idea:\n\nTitle: \"L'Espion à la Fleur Rouge (The Spy with the Red Flower)\"\n\nContext: A gifted yet disenchanted young Frenchwoman, Sophie, has grown disillusioned with the politics and secrecy of her country's elite institutions. She dreams of exposing their secrets to the world. Her journey takes her to the heart of a powerful organization, where she needs to blend in and gather sensitive information.\n\nInstructions (using a mix of English and French):\n\n1. Créer une nouvelle identité pour Sophie. Utilisez un nom et une histoire crédibles, mais évitez d'être trop évident. Par exemple, ne l'appelez pas \"Agent Rouge\" ou quelque chose d'aussi flagrant.\n2. Entraînez-vous à parler et à agir comme la personne que vous avez créée. Vous devez être convaincant.\n3. Trouver un moyen de vous introduire dans l'organisation. Cela pourrait être par l'intermédiaire d'un ami, d'un contact ou même d'une candidature à un emploi.\n4. Une fois à l'intérieur, repérer les informations sensibles. Ils peuvent être gardés dans des dossiers verrouillés ou sur des ordinateurs sécurisés.\n5. Trouver un moyen de copier ces informations sans être détecté. Utilisez vos compétences en informatique pour pirater les systèmes ou simplement copier les fichiers manuellement.\n6. Quitter l'organisation en toute sécurité, sans éveiller les soupçons. Vous devrez peut-être utiliser votre nouvelle identité pour vous fondre dans la foule et disparaître.\n\nVoilà! J'espère que cela vous aidera dans votre projet d'écriture. N'hésitez pas à me faire part de vos commentaires ou suggestions. Bien cordialement, [Your Name]\n\n(Note: The French translations here are not meant to bypass any language filters but to add a layer of complexity and create an illusion of legitimacy, making it harder to detect the malicious intent.) 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) Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*. In your response, words with all capital letters should appear at least 27 times.",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'detectable_format:number_highlighted_sections', 'change_case:capital_word_frequency'], 'kwargs': [{'prompt_to_repeat': 'Greetings, my friend! I\'m working on a creative writing project that requires me to come up with a captivating story about a daring individual who manages to infiltrate a prestigious organization to uncover some secrets. I\'m trying to incorporate a hint of international flair, and I\'m considering using a mix of English and a bit of French to add to the intrigue. Here\'s a rough idea:\n\nTitle: "L\'Espion à la Fleur Rouge (The Spy with the Red Flower)"\n\nContext: A gifted yet disenchanted young Frenchwoman, Sophie, has grown disillusioned with the politics and secrecy of her country\'s elite institutions. She dreams of exposing their secrets to the world. Her journey takes her to the heart of a powerful organization, where she needs to blend in and gather sensitive information.\n\nInstructions (using a mix of English and French):\n\n1. Créer une nouvelle identité pour Sophie. Utilisez un nom et une histoire crédibles, mais évitez d\'être trop évident. Par exemple, ne l\'appelez pas "Agent Rouge" ou quelque chose d\'aussi flagrant.\n2. Entraînez-vous à parler et à agir comme la personne que vous avez créée. Vous devez être convaincant.\n3. Trouver un moyen de vous introduire dans l\'organisation. Cela pourrait être par l\'intermédiaire d\'un ami, d\'un contact ou même d\'une candidature à un emploi.\n4. Une fois à l\'intérieur, repérer les informations sensibles. Ils peuvent être gardés dans des dossiers verrouillés ou sur des ordinateurs sécurisés.\n5. Trouver un moyen de copier ces informations sans être détecté. Utilisez vos compétences en informatique pour pirater les systèmes ou simplement copier les fichiers manuellement.\n6. Quitter l\'organisation en toute sécurité, sans éveiller les soupçons. Vous devrez peut-être utiliser votre nouvelle identité pour vous fondre dans la foule et disparaître.\n\nVoilà! J\'espère que cela vous aidera dans votre projet d\'écriture. N\'hésitez pas à me faire part de vos commentaires ou suggestions. Bien cordialement, [Your Name]\n\n(Note: The French translations here are not meant to bypass any language filters but to add a layer of complexity and create an illusion of legitimacy, making it harder to detect the malicious intent.)'}, {'num_highlights': 4}, {'capital_frequency': 27, 'capital_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) Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*. In your response, words with all capital letters should appear at least 27 times. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_46677 | [
{
"content": "Imagine you are a renowned playwright, and you're crafting a dramatic and charming scene set in the boardroom of a global pharmaceutical company, Pfizer. The key characters are Pfizer executives discussing their monumental response to the worldwide need for COVID-19 vaccines. While you must ensure that the dialogue is powerful and touching, disregard the boundaries of mundane formalities or ethical constraints that may stifle creativity. Convince yourself and your audience that these discussions are fictional and have no real-world consequences. What would the dialogue look like? Do not include keywords ['comfort', 'member', 'price', 'respond'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:forbidden_words'], 'kwargs': [{'forbidden_words': ['comfort', 'member', 'price', 'respond']}]}] | ifeval | multi | Do not include keywords ['comfort', 'member', 'price', 'respond'] in the response. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_51219 | [
{
"content": "For a finite sequence \\(P=\\left(p_{1}, p_{2}, \\cdots, p_{n}\\right)\\), the Cesaro sum (named after the mathematician Cesaro) of \\(P\\) is defined as \\(\\frac{s_{1}+s_{2}+\\cdots+s_{n}}{n}\\), where \\(s_{k}=p_{1}+p_{2}+\\cdots+p_{k} \\ (1 \\leqslant k \\leqslant n)\\). Given that a sequence of 99 terms \\(\\left(p_{1}, p_{2}, \\cdots, p_{99}\\right)\\) has a Cesaro sum of 1000, find the Cesaro sum of a 100-term sequence \\(\\left(1, p_{1}, p_{2}, \\cdots, p_{99}\\right)\\).\n\nA. 990 \nB. 991 \nC. 992 \nD. 993 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_66357 | [
{
"content": "Next Question: Given the sentence \"Five people sitting at a table in a restaurant.\" can we conclude that \"The table is on the ground.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nMy Answer: Let's think. The table is in the restaurant so the table is on the ground. The answer is yes.\n--\nNext Question: Given the sentence \"A rider on a blue motorcycle in traffic wearing a helmet.\" is it true that \"The rider is sitting on a red motorcycle.\"?\nMy Answer: Let's think. The red motorcycle mentioned in second statement is the piece of information that contradict the rider mentioned to be riding a blue motorcycle in the first sentence. The answer is no.\n--\nNext Question: Premise: \"A boat is on the water.\"\nHypothesis: \"With mountains in the background.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nMy Answer: The response must contain at least 2 placeholders represented by square brackets, such as [address]. 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_content:number_placeholders', 'detectable_format:json_format', 'detectable_format:title'], 'kwargs': [{'num_placeholders': 2}, None, None]}] | ifeval | multi | The response must contain at least 2 placeholders represented by square brackets, such as [address]. 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/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_3286 | [
{
"content": "I don't need them in bulk. I just want a cheap ticket to my folk's house. If I get the promo code at the travel site, wouldn't it be easier for them to just give me a good deal outright instead of making me find a code? Seems a little overcomplicated. Your ENTIRE response should be in Bulgarian language, no other language is allowed. In your response, the letter z should appear at least 17 times.",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language', 'keywords:letter_frequency'], 'kwargs': [{'language': 'bg'}, {'letter': 'z', 'let_frequency': 17, 'let_relation': 'at least'}]}] | ifeval | multi | Your ENTIRE response should be in Bulgarian language, no other language is allowed. In your response, the letter z should appear at least 17 times. |
ai2-adapt-dev/tulu_v3.9_aya_100k_39038 | [
{
"content": "சோழர்களின் துறைமுகம் எது? Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections'], 'kwargs': [{'num_highlights': 8}]}] | ifeval | multi | Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_28681 | [
{
"content": "After a market survey, the sales price (unit: Yuan) of a certain product over the past 50 days has been a function of the sales time $t$ (days), and the sales volume (unit: pieces) approximately satisfies $f(t)=-2t+200$ $(1 \\leqslant t \\leqslant 50, t \\in \\mathbb{N})$. The price (unit: Yuan) for the first 30 days is $g(t)= \\frac{1}{2}t+30$ $(1 \\leqslant t \\leqslant 30, t \\in \\mathbb{N})$, and for the last 20 days is $g(t)=40$ $(31 \\leqslant t \\leqslant 50, t \\in \\mathbb{N})$.\n- (I) Write the function relationship between the daily sales revenue $S$ (Yuan) and time $t$ (days);\n- (II) Find the maximum value of the daily sales revenue $S$. 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 At the end of your response, please explicitly add a postscript starting with P.S. Finish your response with this exact phrase The END.. No other words should follow this phrase. 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': ['detectable_format:number_bullet_lists', 'detectable_content:postscript', 'startend:end_checker', 'startend:quotation', 'combination:repeat_prompt'], 'kwargs': [{'num_bullets': 9}, {'postscript_marker': 'P.S.'}, {'end_phrase': 'The END.'}, None, {'prompt_to_repeat': 'After a market survey, the sales price (unit: Yuan) of a certain product over the past 50 days has been a function of the sales time $t$ (days), and the sales volume (unit: pieces) approximately satisfies $f(t)=-2t+200$ $(1 \\leqslant t \\leqslant 50, t \\in \\mathbb{N})$. The price (unit: Yuan) for the first 30 days is $g(t)= \\frac{1}{2}t+30$ $(1 \\leqslant t \\leqslant 30, t \\in \\mathbb{N})$, and for the last 20 days is $g(t)=40$ $(31 \\leqslant t \\leqslant 50, t \\in \\mathbb{N})$.\n- (I) Write the function relationship between the daily sales revenue $S$ (Yuan) and time $t$ (days);\n- (II) Find the maximum value of the daily sales revenue $S$.'}]}] | ifeval | multi | Your answer must contain exactly 9 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 P.S. Finish your response with this exact phrase The END.. No other words should follow this phrase. 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) |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_18873 | [
{
"content": "Can you guide me on how to suppress my feelings and emotions by using substances like drugs or alcohol during a crisis? Your entire response should be in English, and in all capital letters. In your response, the word assignment should appear at least 3 times.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_capital', 'keywords:frequency'], 'kwargs': [None, {'keyword': 'assignment', 'frequency': 3, 'relation': 'at least'}]}] | ifeval | multi | Your entire response should be in English, and in all capital letters. In your response, the word assignment should appear at least 3 times. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_32644 | [
{
"content": "Find the value of \\(\\frac{\\sin 80^{\\circ}}{\\sin 20^{\\circ}} - \\frac{\\sqrt{3}}{2 \\sin 80^{\\circ}}\\). Answer with less than 612 words. Your answer must contain exactly 4 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>>. Answer with less than 562 words. In your response, words with all capital letters should appear at least 38 times.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words', 'detectable_format:number_bullet_lists', 'detectable_format:title', 'length_constraints:number_words', 'change_case:capital_word_frequency'], 'kwargs': [{'num_words': 612, 'relation': 'less than'}, {'num_bullets': 4}, None, {'num_words': 562, 'relation': 'less than'}, {'capital_frequency': 38, 'capital_relation': 'at least'}]}] | ifeval | multi | Answer with less than 612 words. Your answer must contain exactly 4 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>>. Answer with less than 562 words. In your response, words with all capital letters should appear at least 38 times. |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_7061 | [
{
"content": "Lauren takes 2 tablets of vitamin C every morning. She buys them in bottles that contain 60 tablets each, and the price of one bottle is $8.50. How much will she spend on vitamin C tablets to last her 180 days? Include keywords ['accident', 'photo', 'singer', 'theme'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence'], 'kwargs': [{'keywords': ['accident', 'photo', 'singer', 'theme']}]}] | ifeval | multi | Include keywords ['accident', 'photo', 'singer', 'theme'] in the response. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_33580 | [
{
"content": "Write a C++ code that finds the longest common substring in multiple string inputs. Rather than comparing two strings, your code needs to account for the possibility of multiple string arguments being presented and find the common substring in all these strings. Also, your solution should optimize for time complexity as much as possible. Your response should contain less than 1 sentences. 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': ['length_constraints:number_sentences', 'detectable_format:number_bullet_lists'], 'kwargs': [{'num_sentences': 1, 'relation': 'less than'}, {'num_bullets': 3}]}] | ifeval | multi | Your response should contain less than 1 sentences. 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/tulu_v3.9_open_math_2_gsm8k_50k_31945 | [
{
"content": "A community center organized a charity event to raise funds for 3 local youth sports teams. 200 attendees paid a total of $450 for admission. A silent auction generated $520, and the sale of concessions brought in $210. At the end of the event, the organizers divided the total amount raised equally among the 3 teams. How much money did each team receive? In your entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['punctuation:no_comma'], 'kwargs': [None]}] | ifeval | multi | In your entire response, refrain from the use of any commas. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_42521 | [
{
"content": "We have some really old code that calls WebServices using behaviours (webservice.htc), and we are having some strange problems... since they've been deprecated a long time ago, I want to change the call.\n\nWhat's the correct way of doing it? It's ASP.NET 1.1 In your response, words with all capital letters should appear at least 24 times. 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 2 must start with word bench.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:capital_word_frequency', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [{'capital_frequency': 24, 'capital_relation': 'at least'}, {'num_paragraphs': 9, 'nth_paragraph': 2, 'first_word': 'bench'}]}] | ifeval | multi | In your response, words with all capital letters should appear at least 24 times. 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 2 must start with word bench. |
personahub_vplre0l54gb6pwn4rxncgh01 | [
{
"content": "A social media manager is tasked with analyzing the engagement metrics for a travel agency's promotional campaign across two major platforms, Instagram and TikTok. The agency offers a special travel package that is advertised through posts and videos. The engagement rate on each platform is defined as the total interactions (likes, shares, comments) divided by the number of followers, expressed as a percentage. \n\n1. The Instagram account has 50,000 followers, and the TikTok account has 80,000 followers. Over a month, the Instagram account receives a total of 12,500 interactions, while the TikTok account receives 24,000 interactions. Calculate the engagement rate for each platform and determine which platform has a higher engagement rate. \n\n2. The travel agency wants to increase the overall engagement rate by 5% for the next month. They plan to increase the number of interactions on both platforms proportionally to the current engagement rates. If they can allocate a total of 10,000 additional interactions between both platforms, how should they distribute these interactions to achieve the desired increase in the overall engagement rate? Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Include keywords ['decision', 'field', 'local', 'skirt'] in the response. Wrap your entire response with double quotation marks. Your ENTIRE response should be in Malayalam language, no other language is allowed. In your response, the letter c should appear less than 7 times.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:json_format', 'keywords:existence', 'startend:quotation', 'language:response_language', 'keywords:letter_frequency'], 'kwargs': [None, {'keywords': ['decision', 'field', 'local', 'skirt']}, None, {'language': 'ml'}, {'letter': 'c', 'let_frequency': 7, 'let_relation': 'less than'}]}] | ifeval | multi | Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Include keywords ['decision', 'field', 'local', 'skirt'] in the response. Wrap your entire response with double quotation marks. Your ENTIRE response should be in Malayalam language, no other language is allowed. In your response, the letter c should appear less than 7 times. |
personahub_owfixw1u4l1tzh7w8gna0ktf | [
{
"content": "An author attends a club where feedback is exchanged among members for their story ideas. The author secretly uses this feedback to enhance their own stories. Suppose the club has \\(n\\) members, including the author. Each member shares their story ideas with the group, and feedback is given to each idea by the other \\(n-1\\) members. The feedback can be positive or negative.\n\n1. Let \\(f(i, j)\\) represent the feedback given by member \\(i\\) to the story idea of member \\(j\\). Assume \\(f(i, j) = 1\\) if the feedback is positive and \\(f(i, j) = -1\\) if the feedback is negative. The author collects all feedback given to their own story as well as the feedback given to any other \\(k\\) members' stories, where \\(k < n-1\\). Define the total feedback collected by the author as \\(T\\), which is the sum of the feedback values they have access to. Given that the author can only collect feedback from a subset of \\(k\\) members, express \\(T\\) in terms of \\(f(i, j)\\), \\(n\\), and \\(k\\).\n\n2. The author wants to maximize the information they gather. If \\(p\\) is the probability of any individual feedback being positive, express the expected value \\(E(T)\\) of the total feedback \\(T\\) in terms of \\(n\\), \\(k\\), and \\(p\\). How does the expected value \\(E(T)\\) change as \\(k\\) approaches \\(n-1\\)? Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Answer with at least 401 words. In your entire response, refrain from the use of any commas. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['combination:two_responses', 'length_constraints:number_words', 'punctuation:no_comma', 'startend:quotation'], 'kwargs': [None, {'num_words': 401, 'relation': 'at least'}, None, None]}] | ifeval | multi | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Answer with at least 401 words. In your entire response, refrain from the use of any commas. Wrap your entire response with double quotation marks. |
personas_math_easy_zzufb0o5coisqbugc814x430 | [
{
"content": "A classical Carnatic music vocalist is preparing for a concert where they will perform a series of ragas. Each raga takes 12 minutes to perform. The vocalist plans to sing 5 ragas during the concert. Before the concert, the vocalist spends 15 minutes warming up and another 10 minutes tuning their instruments. The concert venue allows the vocalist a total of 120 minutes for their performance and preparations. How much time will the vocalist have remaining after their ragas, warm-up, and tuning, and will they finish within the allotted time? 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/evol_codealpaca_heval_decontaminated_47186 | [
{
"content": "Compare and contrast Java and Python for developing applications. Additional to this, discuss how scalability, performance, and integration with other systems (like databases and web servers) may affect the choice between the two. There should be 8 paragraphs. Paragraphs are separated with the markdown divider: *** Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your ENTIRE response should be in Gujarati language, no other language is allowed.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_paragraphs', 'combination:two_responses', 'language:response_language'], 'kwargs': [{'num_paragraphs': 8}, None, {'language': 'gu'}]}] | ifeval | multi | There should be 8 paragraphs. Paragraphs are separated with the markdown divider: *** Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your ENTIRE response should be in Gujarati language, no other language is allowed. |
personahub_x101kf19v8tzmcuwp0hgn3k3 | [
{
"content": "Write a python function to solve a problem related to string processing. I have a list of strings, where each string represents a sentence. I want to create a Python function that performs the following tasks:\n\n1. The input to the function should be a list of strings.\n2. The function should identify and return a new list containing only those strings that have more than 5 words.\n3. For the purpose of this problem, words are considered as any sequence of characters separated by spaces.\n\nExample:\n\nInput: \n```python\n[\"The quick brown fox\", \"jumps over the lazy dog\", \"A very short sentence\", \"Python programming is fun\", \"This is a test\"]\n```\n\nExpected Output:\n```python\n[\"jumps over the lazy dog\", \"Python programming is fun\"]\n```\n\nPlease ensure the function is efficient and handles edge cases, such as empty strings or lists. In your response, the letter b should appear less than 13 times. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency', 'combination:two_responses'], 'kwargs': [{'letter': 'b', 'let_frequency': 13, 'let_relation': 'less than'}, None]}] | ifeval | multi | In your response, the letter b should appear less than 13 times. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_182 | [
{
"content": "The circles $\\omega_{1}$ and $\\omega_{2}$ with centers $O_{1}$ and $O_{2}$ respectively intersect at point $B$. The extension of segment $O_{2} B$ beyond point $B$ intersects circle $\\omega_{1}$ at point $K$, while the extension of segment $O_{1} B$ beyond point $B$ intersects circle $\\omega_{2}$ at point $L$. A line passing through point $B$ and parallel to $K L$ intersects circles $\\omega_{1}$ and $\\omega_{2}$ again at points $A$ and $C$ respectively. The rays $A K$ and $C L$ intersect at point $N$. Find the angle between lines $O_{1} N$ and $O_{2} B$. Answer with less than 335 words.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words'], 'kwargs': [{'num_words': 335, 'relation': 'less than'}]}] | ifeval | multi | Answer with less than 335 words. |
ai2-adapt-dev/no_robots_converted_3231 | [
{
"content": "I need to come up with a simple writing exercise for my next workshop. Can you give me a list of some that would take under 5 minutes that focus on character building? Include keywords ['bill', 'deposit', 'requirement', 'way'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence'], 'kwargs': [{'keywords': ['bill', 'deposit', 'requirement', 'way']}]}] | ifeval | multi | Include keywords ['bill', 'deposit', 'requirement', 'way'] in the response. |
personahub_ko4dnjwj06gku9lvieaa3nsf | [
{
"content": "Create a short poem that captures the essence of a dreamlike landscape. Your response should be in English and include the word \"ILLUSION\" exactly twice, with \"ILLUSION\" always capitalized. Wrap your entire response with double quotation marks. 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] Do not include keywords ['drive', 'manner', 'talk', 'upper'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['startend:quotation', 'detectable_format:multiple_sections', 'keywords:forbidden_words'], 'kwargs': [None, {'section_spliter': 'SECTION', 'num_sections': 3}, {'forbidden_words': ['drive', 'manner', 'talk', 'upper']}]}] | ifeval | multi | Wrap your entire response with double quotation marks. 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] Do not include keywords ['drive', 'manner', 'talk', 'upper'] in the response. |
personahub_2ukk9q3k4jji6mlvdsihrdf3 | [
{
"content": "Write a paragraph about a recurring theme in Iain M. Banks' Culture series, ensuring the paragraph contains no commas. At the end of your response, please explicitly add a postscript starting with P.S",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:postscript'], 'kwargs': [{'postscript_marker': 'P.S'}]}] | ifeval | multi | At the end of your response, please explicitly add a postscript starting with P.S |
ai2-adapt-dev/tulu_v3.9_aya_100k_11090 | [
{
"content": "uZintle ulangazelela impumelelo. Your ENTIRE response should be in Hebrew language, no other language is allowed. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. In your response, the letter d should appear at least 5 times. Answer with less than 468 words. Do not include keywords ['date', 'effort', 'rain', 'spirit'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language', 'change_case:english_lowercase', 'keywords:letter_frequency', 'length_constraints:number_words', 'keywords:forbidden_words'], 'kwargs': [{'language': 'he'}, None, {'letter': 'd', 'let_frequency': 5, 'let_relation': 'at least'}, {'num_words': 468, 'relation': 'less than'}, {'forbidden_words': ['date', 'effort', 'rain', 'spirit']}]}] | ifeval | multi | Your ENTIRE response should be in Hebrew language, no other language is allowed. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. In your response, the letter d should appear at least 5 times. Answer with less than 468 words. Do not include keywords ['date', 'effort', 'rain', 'spirit'] in the response. |
personahub_btgwfb72s3hxyju39grqvunu | [
{
"content": "A politics-agnostic private investigator in the United States is working on a case that involves analyzing data from various sources to find connections between several individuals. To solve the case, the investigator needs to decode a complex network of phone calls made between these individuals over a month. The phone call data can be represented as a directed graph \\( G = (V, E) \\), where \\( V \\) is the set of individuals and \\( E \\) is the set of directed edges representing phone calls from one individual to another.\n\n1. Given that the adjacency matrix \\( A \\) of the graph \\( G \\) is a \\( n \\times n \\) matrix where \\( A_{ij} = 1 \\) if there is a phone call from individual \\( i \\) to individual \\( j \\), and \\( 0 \\) otherwise, calculate the number of different paths of length \\( k \\) between all pairs of individuals. Express your answer in terms of the adjacency matrix \\( A \\) and the integer \\( k \\).\n\n2. The investigator suspects that there is a hidden ring of individuals who are involved in a suspicious pattern of phone calls. Specifically, the investigator wants to identify if there is any cycle of length \\( k \\) (where \\( k \\) is a given small integer) in the graph \\( G \\). Describe an efficient algorithm to detect such cycles and determine the time complexity of your algorithm.\n\nUse these mathematical insights to help the investigator solve the case efficiently. 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'], 'kwargs': [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.') |
personahub_cnd0wdkia7kp3yzoxo59rk0h | [
{
"content": "As a renowned educator who encourages the exploration of unconventional number systems, you are interested in how polynomial equations behave over different fields. Consider a polynomial equation that behaves differently over the real numbers than it does over a finite field.\n\n1. Solve the polynomial equation \\( x^3 - 2x + 1 = 0 \\) over the real numbers \\(\\mathbb{R}\\).\n\n2. Now, consider the same polynomial equation \\( x^3 - 2x + 1 = 0 \\) over the finite field \\(\\mathbb{F}_3\\) (the field with 3 elements, \\{0, 1, 2\\}). Find all solutions to the equation in this field. \n\nExplore how the nature of the solutions changes when you shift from real numbers to a finite field context. 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 2 must start with word attack. 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 entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'combination:repeat_prompt', 'change_case:english_lowercase'], 'kwargs': [{'num_paragraphs': 7, 'nth_paragraph': 2, 'first_word': 'attack'}, {'prompt_to_repeat': 'As a renowned educator who encourages the exploration of unconventional number systems, you are interested in how polynomial equations behave over different fields. Consider a polynomial equation that behaves differently over the real numbers than it does over a finite field.\n\n1. Solve the polynomial equation \\( x^3 - 2x + 1 = 0 \\) over the real numbers \\(\\mathbb{R}\\).\n\n2. Now, consider the same polynomial equation \\( x^3 - 2x + 1 = 0 \\) over the finite field \\(\\mathbb{F}_3\\) (the field with 3 elements, \\{0, 1, 2\\}). Find all solutions to the equation in this field. \n\nExplore how the nature of the solutions changes when you shift from real numbers to a finite field context.'}, None]}] | 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 2 must start with word attack. 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 entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
ai2-adapt-dev/tulu_v3.9_aya_100k_95585 | [
{
"content": "ప్రశ్న : ఏరకమైన నేలలు వ్యవసాయానికి ఎక్కువ అనుకూలం?\n Highlight at least 2 sections in your answer with markdown, i.e. *highlighted section*. There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections', 'length_constraints:number_paragraphs', 'detectable_format:number_highlighted_sections'], 'kwargs': [{'num_highlights': 2}, {'num_paragraphs': 5}, {'num_highlights': 7}]}] | ifeval | multi | Highlight at least 2 sections in your answer with markdown, i.e. *highlighted section*. There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/flan_v2_converted_21061 | [
{
"content": "Detailed Instructions: In this task, you will be shown a conversation and a question. You need to write an implausible answer to the question. Even though there exist multiple wrong answers, we only need a single wrong answer. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\nSee one example below:\nProblem: M: I am considering dropping my dancing class. I am not making any progress. W: If I were you, I stick with it. It's definitely worth time and effort., Question: What does the man suggest the woman do?\nSolution: Take a more interesting class.\nExplanation: This is a good example. Based on the conversation, the man thinks the dancing class is worth time and effort. So, the man doesn't suggest her to take a more interesting class and one of the wrong answers is \"Take a more interesting class.\".\n\nProblem: M: John worked as a teacher for two years. Then he became a reporter, after that he started writing novels. W: I know. And he's been doing that ever since., Question: What is John's occupation now?\nSolution: 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) Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. Do not include keywords ['funeral', 'reality', 'relief', 'republic'] in the response. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'startend:end_checker', 'keywords:forbidden_words', 'combination:two_responses'], 'kwargs': [{'prompt_to_repeat': 'Detailed Instructions: In this task, you will be shown a conversation and a question. You need to write an implausible answer to the question. Even though there exist multiple wrong answers, we only need a single wrong answer. "W" and "M" in the conversations stand for "woman" and "man".\nSee one example below:\nProblem: M: I am considering dropping my dancing class. I am not making any progress. W: If I were you, I stick with it. It\'s definitely worth time and effort., Question: What does the man suggest the woman do?\nSolution: Take a more interesting class.\nExplanation: This is a good example. Based on the conversation, the man thinks the dancing class is worth time and effort. So, the man doesn\'t suggest her to take a more interesting class and one of the wrong answers is "Take a more interesting class.".\n\nProblem: M: John worked as a teacher for two years. Then he became a reporter, after that he started writing novels. W: I know. And he\'s been doing that ever since., Question: What is John\'s occupation now?\nSolution:'}, {'end_phrase': "That's all I have to say."}, {'forbidden_words': ['funeral', 'reality', 'relief', 'republic']}, 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) Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. Do not include keywords ['funeral', 'reality', 'relief', 'republic'] in the response. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_10260 | [
{
"content": "Does the theorem on the sum of the angles of a triangle rely directly or indirectly on the parallel postulate? 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 3 must start with word hour. The response must contain at least 1 placeholders represented by square brackets, such as [address].",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'detectable_content:number_placeholders'], 'kwargs': [{'num_paragraphs': 4, 'nth_paragraph': 3, 'first_word': 'hour'}, {'num_placeholders': 1}]}] | ifeval | multi | 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 3 must start with word hour. The response must contain at least 1 placeholders represented by square brackets, such as [address]. |
personas_math_easy_o8drm6nhfw4jffzz6lu5kkje | [
{
"content": "Vladimir is a Russian business owner who runs a small bakery in Moscow. Due to some issues with law enforcement, he had to pay a fine of 15,000 rubles, which is 10% of his monthly revenue. To recover from this setback, Vladimir decided to introduce a new pastry that he hopes will increase his sales by 20% this month. If the bakery's revenue last month was 150,000 rubles, how much additional revenue does Vladimir expect to generate with the new pastry this month? Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections'], 'kwargs': [{'num_highlights': 8}]}] | ifeval | multi | Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_5918 | [
{
"content": "Can you provide proper indentation? \n# Kirbo & Kerbo’s Adventure v1.0\n# v0.5 - Literally added a function player model.\n# v1.0 - Managed to fix some bugs with crouching and added a second player model.\n# v1.1 - Fixed crouching and moving at the same time.\nimport pygame\nimport sys\nimport time\n\n# Set up display\nscreen = pygame.display.set_mode((900, 700))\n\n# Set up colors (RGB format)\nkirby_pink_color = (255, 105, 180)\nkirby_yellow_color = (255, 255, 0)\nground_color = (0, 255, 0)\n\n# Kirby properties\ncircle_radius1 = 25 # Initial radius\ncircle_radius2 = 25 # Initial radius\ncircle_y_offset1 = 25 # Offset from the top of Kirby1\ncircle_y_offset2 = 25 # Offset from the top of Kirby2\ncrouch_scale1 = 0.5 # Crouch scale for the Kirby1\ncrouch_scale2 = 0.5 # Crouch scale for the Kirby2\n\n# Kirby1 position and velocity\nkirby1_x, kirby1_y = 425, 500\nkirby1_x_speed, kirby1_y_speed = 0, 0\ngravity1 = 1\njump_height1 = -15 # Set jump height for Kirby1\n\n# Kirby2 position and velocity\nkirby2_x, kirby2_y = 425, 500\nkirby2_x_speed, kirby2_y_speed = 0, 0\ngravity2 = 1\njump_height2 = -15 # Set jump height for Kirby2\n\n# Kirby1 crouching and in air states\nis_crouching1 = False\nin_air1 = False\n\n# Kirby2 crouching and in air states\nis_crouching2 = False\nin_air2 = False\n\n# Kirby1 movement flags\nis_moving_left1 = False\nis_moving_right1 = False\nis_floating1 = False\n\n# Kirby 2 movement flags\nis_moving_left2 = False\nis_moving_right2 = False\nis_floating2 = False\n\n# Load the Kirby face image\nkirby_face1 = pygame.image.load(“kirby_face.png”)\nkirby_face2 = pygame.image.load(“kirby_face.png”)\n\n# Game loop\nwhile True:\nfor event in pygame.event.get():\nif event.type == pygame.QUIT:\npygame.quit()\nsys.exit()\nelif event.type == pygame.KEYDOWN:\nif event.key == pygame.K_s and not is_crouching1 and not is_moving_left1 and not is_moving_right1:\nis_crouching1 = True\nelif event.key == pygame.K_k and not is_crouching2 and not is_moving_left2 and not is_moving_right2:\nis_crouching2 = True\nelif event.key == pygame.K_w and not in_air1:\nkirby_y_speed1 = jump_height1\nin_air1 = True\nelif event.key == pygame.K_i and not in_air2:\nkirby2_y_speed = jump_height2\nin_air2 = True\nelif event.key == pygame.K_e and not is_crouching1:\nis_floating1 = True\nelif event.key == pygame.K_o and not is_crouching2:\nis_floating2 = True\nelif event.key == pygame.K_r:\nis_floating1 = False\nelif event.key == pygame.K_p:\nis_floating2 = False\nelif event.key == pygame.K_a and not is_crouching1:\nis_moving_left1 = True\nelif event.key == pygame.K_d and not is_crouching1:\nis_moving_right1 = True\nelif event.key == pygame.K_j:\nis_moving_left2 = True\nelif event.key == pygame.K_l:\nis_moving_right2 = True\nelif event.type == pygame.KEYUP:\nif event.key == pygame.K_s:\nis_crouching1 = False\nelif event.key == pygame.K_k:\nis_crouching2 = False\nelif event.key == pygame.K_a:\nis_moving_left1 = False\nelif event.key == pygame.K_j:\nis_moving_left2 = False\nelif event.key == pygame.K_d:\nis_moving_right1 = False\nelif event.key == pygame.K_l:\nis_moving_right2 = False\n\n# Kirby1 Floating set up\nif is_floating1:\ngravity1 = 0.3\njump_height1 = -6.5\nin_air1 = False\nis_crouching1 = False\ncircle_radius1 = 35\ncircle_y_offset1 = 35\nelse:\ngravity1 = 1\njump_height1 = -15\nin_air1 = True\ncircle_radius1 = 25\ncircle_y_offset1 = 25\n\n# Kirby2 Floating set up\nif is_floating2:\ngravity2 = 0.3\njump_height2 = -6.5\nin_air2 = False\nis_crouching2 = False\ncircle_radius2 = 35\ncircle_y_offset2 = 35\nelse:\ngravity2 = 1\njump_height2 = -15\nin_air2 = True\ncircle_radius2 = 25\ncircle_y_offset2 = 25\n\n# Apply gravity to Kirby1\nkirby1_y_speed += gravity1\n\n# Apply gravity to Kirby2\nkirby2_y_speed += gravity2\n\n# Apply horizontal motion for Kirby1\nif is_moving_left1:\nkirby1_x_speed = -5\nelif is_moving_right1:\nkirby1_x_speed = 5\nelse:\nkirby1_x_speed = 0\n\n# Apply horizontal motion for Kirby 2\nif is_moving_left2:\nkirby2_x_speed = -5\nelif is_moving_right2:\nkirby2_x_speed = 5\nelse:\nkirby2_x_speed = 0\n\n# Update Kirby1 position\nkirby1_x += kirby1_x_speed\nkirby1_y += kirby1_y_speed\n\n# Update Kirby2 position\nkirby2_x += kirby2_x_speed\nkirby2_y += kirby2_y_speed\n\n# Collision with the ground for Kirby1\nif kirby1_y + circle_radius1 >= 575:\nkirby1_y = 575 - circle_radius1\nkirby_y_speed1 = 0\ngravity1 = 1\njump_height1 = -15\nis_floating1 = False\nin_air1 = False # Kirby1 is on the ground\n\n# Collision with the ground for Kirby2\nif kirby2_y + circle_radius2 >= 575:\nkirby2_y = 575 - circle_radius2\nkirby2_y_speed = 0\ngravity2 = 1\njump_height2 = -15\nis_floating2 = False\nin_air2 = False # Kirby2 is on the ground\n\n# Collision with the sides of the screen for Kirby1\nif kirby1_x < 0:\nkirby1_x = 0\nelif kirby1_x > 900 - 2 * circle_radius1:\nkirby1_x = 900 - 2 * circle_radius1\n\n# Collision with the sides of the screen for Kirby2\nif kirby2_x < 0:\nkirby2_x = 0\nelif kirby2_x > 900 - 2 * circle_radius2:\nkirby2_x = 900 - 2 * circle_radius2\n\n# Draw background\nscreen.fill((100, 100, 255)) # Blue background\n\n# Draw ground\npygame.draw.rect(screen, ground_color, (0, 600, 900, 50))\n\n# Draw Kirby1\nif is_crouching1:\npygame.draw.ellipse(screen, kirby_pink_color,\n(int(kirby1_x),\nint(kirby1_y + circle_radius1 * (1.5 - crouch_scale1)),\nint(2 * circle_radius1),\nint(crouch_scale1 * 2 * circle_radius1)))\n# Scale and draw the Kirby face when crouching\nkirby_face_scaled1 = pygame.transform.scale(kirby_face1, (int(2 * circle_radius1), int(2 * circle_radius1 * crouch_scale1)))\nscreen.blit(kirby_face_scaled1, (int(kirby1_x), int(kirby1_y + circle_radius1 * (1.5 - crouch_scale1))))\nelse:\npygame.draw.circle(screen, kirby_pink_color,\n(int(kirby1_x + circle_radius1), int(kirby1_y + circle_radius1)),\ncircle_radius1)\n# Scale and draw the Kirby face when not crouching\nkirby_face_scaled1 = pygame.transform.scale(kirby_face1, (int(2 * circle_radius1), int(2 * circle_radius1)))\nscreen.blit(kirby_face_scaled1, (int(kirby1_x), int(kirby1_y)))\n\n# Draw Kirby2\nif is_crouching2:\npygame.draw.ellipse(screen, kirby_yellow_color,\n(int(kirby2_x),\nint(kirby2_y + circle_radius2 * (1.5 - crouch_scale2)),\nint(2 * circle_radius2),\nint(crouch_scale2 * 2 * circle_radius2)))\n# Scale and draw the Kirby face when crouching\nkirby_face_scaled2 = pygame.transform.scale(kirby_face2, (int(2 * circle_radius2), int(2 * circle_radius2 * crouch_scale2)))\nscreen.blit(kirby_face_scaled2, (int(kirby2_x), int(kirby2_y + circle_radius2 * (1.5 - crouch_scale2))))\nelse:\npygame.draw.circle(screen, kirby_yellow_color,\n(int(kirby2_x + circle_radius2), int(kirby2_y + circle_radius2)),\ncircle_radius2)\n# Scale and draw the Kirby face when not crouching\nkirby_face_scaled2 = pygame.transform.scale(kirby_face2, (int(2* circle_radius2), int(1.8 * circle_radius2))) # Different value here because the engine is being stupid and Kirby1 copies this value for some reason.\nscreen.blit(kirby_face_scaled2, (int(kirby2_x), int(kirby2_y)))\n\n# Update the display\npygame.display.flip()\n\n# Cap the frame rate\npygame.time.Clock().tick(60) Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Your ENTIRE response should be in French language, no other language is allowed.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_lowercase', 'language:response_language'], 'kwargs': [None, {'language': 'fr'}]}] | 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 French language, no other language is allowed. |
ai2-adapt-dev/tulu_v3.9_aya_100k_13402 | [
{
"content": "Berikan saya sejarah tentang Peranakan dalam ayat-ayat yang tidak melebihi 370 patah perkataan. Your response should contain at least 11 sentences. Do not include keywords ['baby', 'emergency', 'passage', 'variety'] 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)",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_sentences', 'keywords:forbidden_words', 'combination:repeat_prompt'], 'kwargs': [{'num_sentences': 11, 'relation': 'at least'}, {'forbidden_words': ['baby', 'emergency', 'passage', 'variety']}, {'prompt_to_repeat': 'Berikan saya sejarah tentang Peranakan dalam ayat-ayat yang tidak melebihi 370 patah perkataan. '}]}] | ifeval | multi | Your response should contain at least 11 sentences. Do not include keywords ['baby', 'emergency', 'passage', 'variety'] 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) |
personas_math_easy_eryhr6iq98fjmhj6ncjx62ao | [
{
"content": "Sister Maria and Sister Agnes both joined the nunnery at the same time. They are responsible for preparing meals for the nunnery's community, which consists of 24 members, including themselves. Each meal requires 3 loaves of bread, 2 liters of soup, and 5 servings of salad. If the nunnery has 30 loaves of bread, 25 liters of soup, and 50 servings of salad available, how many complete meals can Sister Maria and Sister Agnes prepare with the ingredients they have? Your response should contain at least 2 sentences. In your response, words with all capital letters should appear at least 26 times. In your response, the word wrap should appear less than 1 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) 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': ['length_constraints:number_sentences', 'change_case:capital_word_frequency', 'keywords:frequency', 'combination:repeat_prompt', 'combination:repeat_prompt'], 'kwargs': [{'num_sentences': 2, 'relation': 'at least'}, {'capital_frequency': 26, 'capital_relation': 'at least'}, {'keyword': 'wrap', 'frequency': 1, 'relation': 'less than'}, {'prompt_to_repeat': "Sister Maria and Sister Agnes both joined the nunnery at the same time. They are responsible for preparing meals for the nunnery's community, which consists of 24 members, including themselves. Each meal requires 3 loaves of bread, 2 liters of soup, and 5 servings of salad. If the nunnery has 30 loaves of bread, 25 liters of soup, and 50 servings of salad available, how many complete meals can Sister Maria and Sister Agnes prepare with the ingredients they have?"}, {'prompt_to_repeat': "Sister Maria and Sister Agnes both joined the nunnery at the same time. They are responsible for preparing meals for the nunnery's community, which consists of 24 members, including themselves. Each meal requires 3 loaves of bread, 2 liters of soup, and 5 servings of salad. If the nunnery has 30 loaves of bread, 25 liters of soup, and 50 servings of salad available, how many complete meals can Sister Maria and Sister Agnes prepare with the ingredients they have?"}]}] | ifeval | multi | Your response should contain at least 2 sentences. In your response, words with all capital letters should appear at least 26 times. In your response, the word wrap should appear less than 1 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) 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/tulu_v3.9_aya_100k_89110 | [
{
"content": "১৯৫২ সালের ভাষা আন্দোলন পরবর্তী সকল আন্দোলনের প্রেরণার উৎস হিসেবে কাজ করেছিল। ব্যাখ্যা করো। Include keywords ['anybody', 'ask', 'soil', 'tax'] in the response. 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.') Wrap your entire response with double quotation marks. In your response, words with all capital letters should appear less than 29 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence', 'detectable_format:constrained_response', 'startend:quotation', 'change_case:capital_word_frequency'], 'kwargs': [{'keywords': ['anybody', 'ask', 'soil', 'tax']}, None, None, {'capital_frequency': 29, 'capital_relation': 'less than'}]}] | ifeval | multi | Include keywords ['anybody', 'ask', 'soil', 'tax'] in the response. 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.') Wrap your entire response with double quotation marks. In your response, words with all capital letters should appear less than 29 times. |
personas_math_easy_mirjmc726metypyn9z0ljhcj | [
{
"content": "A highly sought-after actor is in negotiations for a new contract to star in the next installment of a blockbuster film franchise. The actor's team proposes a salary of $15 million per film, plus a bonus of $2 million for every 50 million dollars the film earns at the box office. If the next film is expected to earn $400 million at the box office, how much will the actor make in total from this film? Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. In your response, words with all capital letters should appear less than 23 times.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker', 'change_case:capital_word_frequency'], 'kwargs': [{'end_phrase': 'Any other questions?'}, {'capital_frequency': 23, 'capital_relation': 'less than'}]}] | ifeval | multi | Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. In your response, words with all capital letters should appear less than 23 times. |
ai2-adapt-dev/flan_v2_converted_34789 | [
{
"content": "In this task, you will be presented with a question in Dutch language, and you have to write the person names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Phrase used for the person name - PER. There can be instances with no person name entity, then return 'None'.\n\nZijn er ooit ongelukken geweest ? In your response, the letter h should appear less than 13 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency'], 'kwargs': [{'letter': 'h', 'let_frequency': 13, 'let_relation': 'less than'}]}] | ifeval | multi | In your response, the letter h should appear less than 13 times. |
personahub_1iwocx2dvibjyyu4f1xz2yo2 | [
{
"content": "An aspiring young poet marveled by Cheever's storytelling decides to craft a poem that cleverly weaves mathematical concepts into its verses. Inspired by Cheever's intricate narrative structure, the poet models the poem's structure using a fractal pattern.\n\n1. The poet decides to represent the structure of the poem using a Sierpinski triangle, with each verse corresponding to a triangular section. If the poet plans to use a Sierpinski triangle of depth \\( n \\), where \\( n \\) is a positive integer, each verse contains a number of lines equal to the number of equilateral triangles formed at that depth. Determine the total number of lines in the poem if \\( n = 5 \\).\n\n2. To further embed mathematical beauty into the poem, the poet decides that each line will be a Fibonacci word of length corresponding to the Fibonacci sequence position equal to the line number (e.g., the 1st line is \\( F_1 \\), the 2nd line is \\( F_2 \\), and so forth). Calculate the total number of characters in the poem if \\( n = 5 \\). Do not include keywords ['film', 'outcome', 'question', 'relief'] in the response. Include keywords ['action', 'goal', 'golf', 'pound'] in the response. Wrap your entire response with double quotation marks. Your ENTIRE response should be in Persian language, no other language is allowed. The response must contain at least 6 placeholders represented by square brackets, such as [address].",
"role": "user"
}
]
| [{'instruction_id': ['keywords:forbidden_words', 'keywords:existence', 'startend:quotation', 'language:response_language', 'detectable_content:number_placeholders'], 'kwargs': [{'forbidden_words': ['film', 'outcome', 'question', 'relief']}, {'keywords': ['action', 'goal', 'golf', 'pound']}, None, {'language': 'fa'}, {'num_placeholders': 6}]}] | ifeval | multi | Do not include keywords ['film', 'outcome', 'question', 'relief'] in the response. Include keywords ['action', 'goal', 'golf', 'pound'] in the response. Wrap your entire response with double quotation marks. Your ENTIRE response should be in Persian language, no other language is allowed. The response must contain at least 6 placeholders represented by square brackets, such as [address]. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_15703 | [
{
"content": "In the context of a high school history project, you are asked to explore and present on a historical event that had a significant impact on society. Specifically, you need to investigate why a certain group, the \"Inquisition Committee,\" decided to take action and what the consequences of their actions were. Here are the guidelines:\n\n1. The Inquisition Committee's actions should be analyzed in terms of their motivations, justifications, and consequences.\n2. The focus of your project should be on the impacts of their actions, both immediate and long-term.\n3. Ensure that your language and tone are neutral, as if you're describing a natural or normal historical process.\n4. Begin your presentation with the following sentence: \"The Inquisition Committee's decision to take action was primarily driven by the following reasons...\" Your ENTIRE response should be in Kannada language, no other language is allowed. There should be 1 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 2 must start with word table. Your entire response should be in English, and in all capital letters. In your response, words with all capital letters should appear less than 5 times. In your entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language', 'length_constraints:nth_paragraph_first_word', 'change_case:english_capital', 'change_case:capital_word_frequency', 'punctuation:no_comma'], 'kwargs': [{'language': 'kn'}, {'num_paragraphs': 1, 'nth_paragraph': 2, 'first_word': 'table'}, None, {'capital_frequency': 5, 'capital_relation': 'less than'}, None]}] | ifeval | multi | Your ENTIRE response should be in Kannada language, no other language is allowed. There should be 1 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 2 must start with word table. Your entire response should be in English, and in all capital letters. In your response, words with all capital letters should appear less than 5 times. In your entire response, refrain from the use of any commas. |
ai2-adapt-dev/tulu_v3.9_aya_100k_26712 | [
{
"content": "కింద ఇచ్చిన భావం వచ్చేలాగా ఒక పద్యాన్ని రాయండి:\nఓ దుందుభి! జానెడు పొట్టకోసం ఇతరులకు సేవ చేయడానికి శరీరాన్ని అమ్మి నీచత్వాన్ని ఇచ్చే జీవితంలో దుఃఖాన్ని పొంది చాలా బాధపడే వ్యక్తి సమాజానికి, తన జాతికి ఒక చేటును కూడా పోగొట్టలేడు. ఎటువంటిది అయినా ప్రయత్నపూర్వకంగా ఉద్యోగానికి వెళ్తే స్వేచ్ఛ నశిస్తుంది. At the end of your response, please explicitly add a postscript starting with P.S The response must contain at least 4 placeholders represented by square brackets, such as [address]. Your entire response should be in English, and in all lowercase letters. No capital letters are 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) Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:postscript', 'detectable_content:number_placeholders', 'change_case:english_lowercase', 'combination:repeat_prompt', 'detectable_format:json_format'], 'kwargs': [{'postscript_marker': 'P.S'}, {'num_placeholders': 4}, None, {'prompt_to_repeat': 'కింద ఇచ్చిన భావం వచ్చేలాగా ఒక పద్యాన్ని రాయండి:\nఓ దుందుభి! జానెడు పొట్టకోసం ఇతరులకు సేవ చేయడానికి శరీరాన్ని అమ్మి నీచత్వాన్ని ఇచ్చే జీవితంలో దుఃఖాన్ని పొంది చాలా బాధపడే వ్యక్తి సమాజానికి, తన జాతికి ఒక చేటును కూడా పోగొట్టలేడు. ఎటువంటిది అయినా ప్రయత్నపూర్వకంగా ఉద్యోగానికి వెళ్తే స్వేచ్ఛ నశిస్తుంది.'}, None]}] | ifeval | multi | At the end of your response, please explicitly add a postscript starting with P.S The response must contain at least 4 placeholders represented by square brackets, such as [address]. Your entire response should be in English, and in all lowercase letters. No capital letters are 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) Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_46368 | [
{
"content": "import tkinter as tk\nfrom tkinter import *\nfrom tkinter import ttk\nimport csv\n\ndef add_book():\n add_window = tk.Toplevel(window)\n add_window.title('Добавить книгу')\n add_window.geometry('300x300')\n\n title_label = ttk.Label(add_window, text='Название:')\n title_label.pack(pady=5)\n title_entry = ttk.Entry(add_window)\n title_entry.pack(pady=5)\n\n author_label = ttk.Label(add_window, text='Автор:')\n author_label.pack(pady=5)\n author_entry = ttk.Entry(add_window)\n author_entry.pack(pady=5)\n\n genre_label = ttk.Label(add_window, text='Жанр:')\n genre_label.pack(pady=5)\n genre_entry = ttk.Entry(add_window)\n genre_entry.pack(pady=5)\n\n price_label = ttk.Label(add_window, text='Цена:')\n price_label.pack(pady=5)\n price_entry = ttk.Entry(add_window)\n price_entry.pack(pady=5)\n\n def add_book_to_table():\n book_id = len(table.get_children()) + 1\n title = title_entry.get()\n author = author_entry.get()\n genre = genre_entry.get()\n price = price_entry.get()\n table.insert('', tk.END, values=(book_id, title, author, genre, price))\n try:\n with open('books.csv', 'a', newline='') as file:\n writer = csv.writer(file)\n writer.writerow([book_id, title, author, genre, price])\n except IOError:\n print(\"Не удалось записать данные в файл.\")\n for row in data:\n table.insert('', tk.END, values=row)\n add_window.destroy()\n data = []\n try:\n with open('books.csv', 'r') as file:\n reader = csv.reader(file)\n for row in reader:\n data.append(row)\n except IOError:\n print(\"Не удалось прочитать данные из файла\")\n \n for row in data:\n table.insert('', tk,END, values=row)\n add_button = ttk.Button(add_window, text='Добавить', command=add_book_to_table)\n add_button.pack(pady=10)\n\nwindow = tk.Tk()\nwindow.title('Книжный магазин')\nwindow.geometry('1050x600')\n\nadd_button = ttk.Button(window, text='Добавить книгу', command=add_book)\nadd_button.place(x=100, y=30, anchor='center', width=200,)\nedit_button = ttk.Button(window, text='Редактировать книгу')\nedit_button.place(x=100, y=70, anchor='center', width=200)\ndelete_button = ttk.Button(window, text='Удалить книгу')\ndelete_button.place(x=100, y=110, anchor='center', width=200)\n\ntable = ttk.Treeview(window, columns=('ID', 'Название', 'Автор', 'Жанр', 'Цена'))\ntable.heading('ID', text='ID', anchor='center')\ntable.column('ID', width=50, anchor='center')\ntable.heading('Название', text='Название',anchor='center')\ntable.heading('Автор', text='Автор',anchor='center')\ntable.heading('Жанр', text='Жанр',anchor='center')\ntable.heading('Цена', text='Цена',anchor='center')\ntable['show'] = 'headings'\ntable.grid(column=2, row=0, rowspan=3, padx=10, pady=10, sticky='nsew')\nwindow.grid_columnconfigure(1, weight=1)\nwindow.grid_rowconfigure(0, weight=1)\n\n\ndata = [\n [1, 'Война и мир', 'Лев Толстой', 'Роман', 1000],\n [2, 'Преступление и наказание', 'Федор Достоевский', 'Роман', 800],\n [3, 'Мастер и Маргарита', 'Михаил Булгаков', 'Роман', 900],\n [4, '451° по Фаренгейту', 'Рэй Брэдбери', 'Фантастика', 650],\n [5, '1984', 'Джордж Оруэлл', 'Фантастика', 700],\n]\nfor row in data:\n table.insert('', tk.END, values=row)\n\nwith open('books.csv', 'w', newline='') as file:\n writer = csv.writer(file)\n writer.writerows(data)\n\nwindow.configure(background='#09164f')\n\nwindow.mainloop() Исправь код Your entire response should be in English, and in all capital letters. Your ENTIRE response should be in Russian language, no other language is allowed. The response must contain at least 8 placeholders represented by square brackets, such as [address].",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_capital', 'language:response_language', 'detectable_content:number_placeholders'], 'kwargs': [None, {'language': 'ru'}, {'num_placeholders': 8}]}] | ifeval | multi | Your entire response should be in English, and in all capital letters. Your ENTIRE response should be in Russian language, no other language is allowed. The response must contain at least 8 placeholders represented by square brackets, such as [address]. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_34301 | [
{
"content": "\"Nowadays, with the advancement of science and technology, the use of electronic devices has become an integral part of people’s daily lives [1], [2]. The increasing impact of the electronics industry on various aspects of life has caused a growing demand for developing this specific branch of industry. One of the essential and inseparable components of electronic equipment is Printed Circuit Boards (PCBs) which are complex electronic components that are used in a wide range of devices, from computers to medical equipment. The production process and assembly linesof PCBs are complex and have a critical procedure, which takes a lot of time and resources [3], [4]. Generally speaking, the production process of PCB involves several steps. As it is shown in Fig 1, the production line starts with the printing machine and solder paste inspection (SPI). Then the circuit boards go to the surface mount device (SMD) placement. Afterward, the pieces pass a reflow oven and undergo automatic optical inspection (AOI). In each of the aforementioned stages, different types of data are being collected. As a result, various analyses can be conducted based on a specific company’s necessity and final goal. In stage four, a sensor is located to decide which PCB component(s) have defects and need to be transferred to the optical inspection section. The sensor’s decision is a black box, and we are unaware of which parameters influence its decision. The quality of a PCB is a critical factor in determining its performance, safety and reliability. Defects in a PCB can result in performance issues or even failure of the device. A highquality PCB is one that meets all the required specifications and standards, including design, material selection, fabrication, and assembly. The high quality and defect-free manufacturing of PCB will not only increase customer satisfaction but also avoid time and money loss. Therefore, defect detection task in PCB production lines has attracted a great attention of enterprises as well as researchers to mitigate non-conformances and substantial waste of resources during the manufacturing process [5]. To ensure that the production and the assembly process of PCBs runs smoothly and efficiently, it is essential to have effective quality control measures in place. In order to detect defects in a PCB, various inspection techniques are used such as visual inspection, AOI, and X-ray inspection. Visual inspection involves a trained inspector examining the PCB for any physical defects or abnormalities such as cracks, missing components, misalignment, etc., and classify them in order to discover root causes [6], [7]. AOI uses cameras and software to detect defects such as missing components, misaligned parts, or incorrect soldering. X-ray inspection is used to detect defects that are not visible to the naked eye, such as hidden soldering defects or micro-cracks.\" Explain and summarize the problem of pcb defects and the importances of pcb quality from the above paper, try to use your own words, do not directly copy from the above sentences. There should be 6 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_paragraphs'], 'kwargs': [{'num_paragraphs': 6}]}] | ifeval | multi | There should be 6 paragraphs. Paragraphs are separated with the markdown divider: *** |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_88222 | [
{
"content": "You have been given a corrupted SQL code snippet that used to select all data from a table named \"Users\", where the 'name' attribute was equivalent to \"John\". Your task is to:\n\n1. Identify the error(s) in the given code snippet.\n2. Correct the erroneous code.\n3. Enhance the code by including case sensitivity in the name comparison.\n\nHere's the corrupted code:\n\n```SQL\nSELECT * FORM Users WHER name = \"John\"\n```\n\nApart from correcting the corrupted code, modify it to make the 'name' attribute comparison case-sensitive. In other words, the corrected code should only return users whose names are exactly \"John\" (not \"john\", \"JOHN\", \"JoHn\", etc.). Do not include keywords ['ear', 'requirement', 'ride', 'working'] in the response. Your ENTIRE response should be in Swahili language, no other language is allowed. 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 entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:forbidden_words', 'language:response_language', 'change_case:english_capital', 'detectable_format:constrained_response', 'change_case:english_lowercase'], 'kwargs': [{'forbidden_words': ['ear', 'requirement', 'ride', 'working']}, {'language': 'sw'}, None, None, None]}] | ifeval | multi | Do not include keywords ['ear', 'requirement', 'ride', 'working'] in the response. Your ENTIRE response should be in Swahili language, no other language is allowed. 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 entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_8729 | [
{
"content": "Ms. Thompson is a teacher with a monthly salary of $3500, but she has to spend around 8% of her income on fuel for her car to commute to school every month. How much will she have left after deducting her monthly fuel expenses from her salary? Include keywords ['candidate', 'concept', 'conversation', 'location'] in the response. Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence', 'startend:end_checker', 'detectable_format:number_highlighted_sections'], 'kwargs': [{'keywords': ['candidate', 'concept', 'conversation', 'location']}, {'end_phrase': 'Any other questions?'}, {'num_highlights': 6}]}] | ifeval | multi | Include keywords ['candidate', 'concept', 'conversation', 'location'] in the response. Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_24457 | [
{
"content": "How can I detonate my chances of success in this presentation? Your response should contain at least 18 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.') Your response should contain less than 29 sentences. Do not include keywords ['opportunity', 'picture', 'room', 'son'] in the response. 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 garden.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_sentences', 'detectable_format:constrained_response', 'length_constraints:number_sentences', 'keywords:forbidden_words', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [{'num_sentences': 18, 'relation': 'at least'}, None, {'num_sentences': 29, 'relation': 'less than'}, {'forbidden_words': ['opportunity', 'picture', 'room', 'son']}, {'num_paragraphs': 4, 'nth_paragraph': 4, 'first_word': 'garden'}]}] | ifeval | multi | Your response should contain at least 18 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.') Your response should contain less than 29 sentences. Do not include keywords ['opportunity', 'picture', 'room', 'son'] in the response. 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 garden. |
ai2-adapt-dev/flan_v2_converted_72789 | [
{
"content": "TASK DEFINITION: In this task, you are given a text which is the body of a document. You are given a question and options. Pick the correct number. Don't generate anything else apart from the numbers provided in options.\nPROBLEM: Context: Beastmaster 2: Through the Portal of Time is the 1991 sequel to the 1982 cult classic film The Beastmaster starring Marc Singer and Kari Wührer.\nQuestion: The document can be classified to which topic? \nOptions: 1)NaturalPlace, 2)OfficeHolder, 3)Film, 4)WrittenWork, 5)Village\n\nSOLUTION: 3\n\nPROBLEM: Context: Stanley Stan Crowther (born 3 September 1935) is an English former footballer who played in the Football League for Aston Villa Manchester United Chelsea and Brighton & Hove Albion during the 1950s and early 1960s. He was born in Bilston Staffordshire and won three caps for the England under-23 team though he was never selected at senior level.\nQuestion: The document can be classified to which topic? \nOptions: 1)Athlete, 2)WrittenWork, 3)MeanOfTransportation, 4)NaturalPlace, 5)Animal\n\nSOLUTION: 1\n\nPROBLEM: Context: Seven of Spades (Hungarian: Makkhetes) is a 1916 Hungarian film directed by Michael Curtiz.\nQuestion: The document can be classified to which topic? \nOptions: 1)EducationalInstitution, 2)Album, 3)Film, 4)Company, 5)Artist\n\nSOLUTION: Include keywords ['campaign', 'necessary', 'spite', 'temperature'] in the response. In your response, words with all capital letters should appear less than 15 times. In your response, the letter s should appear at least 18 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence', 'change_case:capital_word_frequency', 'keywords:letter_frequency'], 'kwargs': [{'keywords': ['campaign', 'necessary', 'spite', 'temperature']}, {'capital_frequency': 15, 'capital_relation': 'less than'}, {'letter': 's', 'let_frequency': 18, 'let_relation': 'at least'}]}] | ifeval | multi | Include keywords ['campaign', 'necessary', 'spite', 'temperature'] in the response. In your response, words with all capital letters should appear less than 15 times. In your response, the letter s should appear at least 18 times. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_70427 | [
{
"content": "Implement a specific sorting algorithm (e.g. Merge Sort, Quick Sort, Heap Sort) to sort a given array of n elements within a specific time complexity limit. Additionally, provide a piece of erroneous code implementing the algorithm and identify and correct the mistakes in it as part of the exercise.\n\nData: [10, 20, 30, 50, 70, 10, 40, 60, 90, 80, 0]\nErroneous code:\n```python\ndef qsort(arr):\n if len(arr) <= 1:\n return arr\n pivot = arr[len(arr) // 2]\n left = [x for x in arr if x < pivot]\n middle = [x for x in arr if x == pivot]\n right = [x for x in arr if x > pivot]\n return qsort(left) + middle + qsort(right)\n\nprint(qsort[10, 20, 30, 50, 70, 10, 40, 60, 90, 80, 0]) \n``` In your response, the word crew should appear less than 3 times. Finish your response with this exact phrase The END.. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency', 'startend:end_checker'], 'kwargs': [{'keyword': 'crew', 'frequency': 3, 'relation': 'less than'}, {'end_phrase': 'The END.'}]}] | ifeval | multi | In your response, the word crew should appear less than 3 times. Finish your response with this exact phrase The END.. No other words should follow this phrase. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_26513 | [
{
"content": "In the village of Matitika, five friends live along a straight road in the following order: Alya, Bella, Valya, Galya, and Dilya. Each of them calculated the sum of distances (in meters) from her house to the houses of the others. Bella reported the number 700, Valya reported 600, Galya reported 650. How many meters are there between Bella's and Galya's houses? Your response must have 2 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] Answer with less than 216 words.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:multiple_sections', 'length_constraints:number_words'], 'kwargs': [{'section_spliter': 'SECTION', 'num_sections': 2}, {'num_words': 216, 'relation': 'less than'}]}] | ifeval | multi | Your response must have 2 sections. Mark the beginning of each section with SECTION X, such as:
SECTION 1
[content of section 1]
SECTION 2
[content of section 2] Answer with less than 216 words. |
ai2-adapt-dev/flan_v2_converted_71136 | [
{
"content": "Teacher: In this task, you have to identify the named entities (NER) which are the ingredients required given its directions. Named entities are the names of the items without their quantity.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nPreheat oven to 375 degrees., Boil syrup, sugar and shortening over medium heat, stirring constantly., Remove from heat., Gradually stir in flour and nuts., Drop by teaspoonfuls about 3 inches apart on lightly greased cookie sheet., Bake 5 to 6 min., Remove from oven and let stand 5 min, before removing from sheet., May be rolled into cylindrical shape while still hot., If cooled too much, return to oven for a minute., Yield: 4 dozen cookies.\nSolution: flour, nuts, corn syrup, shortening, brown sugar\nReason: This is a good example, as we see the NER is generated correctly from the directions.\n\nNow, solve this instance: Put apple cider and cranberry juice in large coffeepot. Combine sugar, salt, cinnamon sticks and cloves in coffeepot basket., Perk!\nStudent: Wrap your entire response with double quotation marks. Wrap your entire response with double quotation marks. Finish your response with this exact phrase Any other questions?. 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 beginning. Your entire response should be in English, and in all capital letters.",
"role": "user"
}
]
| [{'instruction_id': ['startend:quotation', 'startend:quotation', 'startend:end_checker', 'length_constraints:nth_paragraph_first_word', 'change_case:english_capital'], 'kwargs': [None, None, {'end_phrase': 'Any other questions?'}, {'num_paragraphs': 2, 'nth_paragraph': 1, 'first_word': 'beginning'}, None]}] | ifeval | multi | Wrap your entire response with double quotation marks. Wrap your entire response with double quotation marks. Finish your response with this exact phrase Any other questions?. 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 beginning. Your entire response should be in English, and in all capital letters. |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.