key
stringlengths 7
86
| messages
listlengths 1
1
| ground_truth
stringlengths 62
261k
| dataset
stringclasses 1
value | constraint_type
stringclasses 1
value | constraint
stringlengths 31
741
|
|---|---|---|---|---|---|
ai2-adapt-dev/flan_v2_converted_79482
|
[
{
"content": "[Question]Hilary is collecting her toenails in a jar to gross out her sister. She can fit 100 toenails in the jar, unless they are from her two big toes, which are twice as big as the rest. She has already filled it with 20 big toenails and 40 regular toenails. How many regular toenails can she fit into the remainder of the jar?\n[Answer]The 20 big toenails take up as much space as 40 regular toenails because 20 x 2 = 40. She has filled up 80 toenails worth because 40 + 40 = 80. She can fit 20 regular toenails in the jar because 100 - 80 = 20. The answer is 20.\nQ: Howard is taking his kindergarten class to the museum on a school trip. He splits the class equally into 3 groups and then each of the groups goes through the museum one student at a time. If the class has 18 students in total and each student takes 4 minutes to go through the museum, then how long, in minutes, does it take each group to go through the museum?\nA: As the groups are equally sized, they must each have 18 students in the class / 3 groups = 6 students in each group. So each group takes 6 students in each group * 4 minutes per each student’s trip = 24 minutes to go through the museum. The answer is 24.\nQuestion: Kaiden and Adriel were to pick a certain number of apples from their farm. After picking 400 apples each, they realized they still had to pick some more, so each picked 3/4 times as many as they had picked earlier. When they checked the pickup truck that was carrying the apples, they found out they still needed to pick 600 apples each to reach the target number. How many apples were they targeting to pick?\nAnswer: When they picked 400 apples each in the first round, they picked a total of 2 * 400 = 800 apples. They picked 3 / 4 * 400 = 300 apples each in the second round. The total number of apples they picked in the second round is 2 * 300 = 600. The total number of apples they'd picked so far is 800 + 600 = 1400. When they checked the pickup truck that was carrying the apples, they found out they still needed to pick 600 apples each to reach the target number, a total of 2 * 600 = 1200. The target number of apples they had to pick is 1200 + 1400 = 2600. The answer is 2600.\n[Question]Matilda bought a smartphone for $300. Then she decided she wouldn't use it anyway and sold it for $255. What percentage of the initial cost did she lose?\n[Answer]The difference between the initial cost and the amount she sold the phone for is $300 - $255 = $45. $45 is (($45 / $300) * 100)% = 15% of $300. The answer is 15.\nQ: Max can trade 3 coconuts for a crab and 6 crabs for a goat. If he has 342 coconuts and he wants to convert all of them into goats, how many goats will he have?\nA: First find the number of crabs Max can get by dividing the number of coconuts by the exchange rate with crabs: 342 coconuts / 3 coconuts / crab = 114 crabs. Then divide the number of crabs by the exchange rate with goats: 114 crabs / 6 crabs / goat = 19 goats. The answer is 19.\nQuestion: Lydia has 80 plants. 40% of her plants are flowering plants. Lydia wants to place a fourth of her flowering plants on the porch. If each flowering plant produces 5 flowers, how many flowers are there in total on the porch?\nAnswer: The first word of each sentence should be the word associate.",
"role": "user"
}
] |
[{'instruction_id': ['first_word:first_word_sent'], 'kwargs': [{'first_word': 'associate'}]}]
|
ifeval
|
multi
|
The first word of each sentence should be the word associate.
|
personas_math_easy_r9pdipgwklykjrkqi436cbt0
|
[
{
"content": "Ms. Parker, a teacher who values health education, is planning a healthy eating project with her class. She wants to create a fruit salad using apples, bananas, and oranges. For every fruit salad bowl, she uses 3 apples, 2 bananas, and 4 oranges. If Ms. Parker has 18 apples, 20 bananas, and 24 oranges, how many complete fruit salad bowls can she make with the fruits she has? Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. At the end of your response, please explicitly add a postscript starting with P.S. Do not include keywords ['drawer', 'fat', 'meaning', 'soup'] in the response.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:json_format', 'detectable_content:postscript', 'keywords:forbidden_words'], 'kwargs': [None, {'postscript_marker': 'P.S.'}, {'forbidden_words': ['drawer', 'fat', 'meaning', 'soup']}]}]
|
ifeval
|
multi
|
Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. At the end of your response, please explicitly add a postscript starting with P.S. Do not include keywords ['drawer', 'fat', 'meaning', 'soup'] in the response.
|
personas_math_easy_mlmlr5vj85hrtg45ew0usisf
|
[
{
"content": "A former student of Mr. Cockshut remembered that during one of his math classes, Mr. Cockshut brought in a jar of colorful marbles to teach them about division and multiplication. The jar contained 120 marbles in total. Mr. Cockshut divided these marbles equally among 6 groups for a class activity. After the activity, each group was asked to return 3 marbles back to the jar. How many marbles were returned to the jar in total, and how many marbles were left in the hands of each group after returning the marbles? In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Finish your response with this exact phrase The END.. No other words should follow this phrase. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. In your response, the word treat should appear at least 3 times.",
"role": "user"
}
] |
[{'instruction_id': ['punctuation:punctuation_dot', 'paragraphs:paragraphs', 'startend:end_checker', 'detectable_format:bigram_wrapping', 'keywords:frequency'], 'kwargs': [None, {}, {'end_phrase': 'The END.'}, None, {'keyword': 'treat', 'frequency': 3, 'relation': 'at least'}]}]
|
ifeval
|
multi
|
In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Finish your response with this exact phrase The END.. No other words should follow this phrase. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. In your response, the word treat should appear at least 3 times.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_71829
|
[
{
"content": "ڪيميائي ۽ جسماني تبديلي جي وچ ۾ ڇا فرق آهي؟ Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Include keyword film in the 17-th sentence, as the 4-th word of that sentence. The last word of your response should be the word ladder. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:title', 'keywords:keyword_specific_position', 'last_word:last_word_answer', 'paragraphs:paragraphs', 'detectable_format:bigram_wrapping'], 'kwargs': [None, {'keyword': 'film', 'n': 17, 'm': 4}, {'last_word': 'ladder'}, {}, None]}]
|
ifeval
|
multi
|
Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Include keyword film in the 17-th sentence, as the 4-th word of that sentence. The last word of your response should be the word ladder. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>.
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_82901
|
[
{
"content": "I am in the unfortunate situation to use an older Apache httpd 2.4.8, and want to use expressions such as base64 encoding with mod_headers.\nAccording to the documentation expr=value support was added to mod_headers in 2.4.10. What might be a viable solution to get the following configuration running on 2.4.8?\n\nHeader add Set-Cookie \"expr=MYCOOKIE=%{base64:%{env:SOMEENVIRONMENT}}; path=/; Expires=Tue, 19 Jan 2038 04:14:00 GMT;\"\n\n\nThis example is over-simplified. The real expression involves additional unescape and unbase64 functions. It would be cool if someone could give me a hint about if this is possible with 2.4.8 at all and what might be a feasible way implement this.\nThank you!\nMirko\n- Your ENTIRE response should be in Ukrainian language, no other language is allowed. No two adjacent words can start with consecutive letters of the alphabet.",
"role": "user"
}
] |
[{'instruction_id': ['language:response_language', 'keywords:no_adjacent_consecutive'], 'kwargs': [{'language': 'uk'}, None]}]
|
ifeval
|
multi
|
Your ENTIRE response should be in Ukrainian language, no other language is allowed. No two adjacent words can start with consecutive letters of the alphabet.
|
personahub_69019j2l95ds9qh80smlem2w
|
[
{
"content": "As a history major researching religious conflicts, you come across a series of historical documents detailing the number of conflicts over several centuries. You notice a pattern and decide to model it mathematically. \n\n1. You hypothesize that the number of religious conflicts \\( C \\) in a given century \\( x \\) can be modeled by the quadratic equation \\( C(x) = -2x^2 + 12x + 15 \\). Determine the centuries in which the number of conflicts was at least 45. Represent these centuries as an inequality and solve for \\( x \\).\n\n2. Additionally, during your research, you find that the ratio of the number of conflicts in the 15th century to the 10th century can be represented by a rational expression. If the number of conflicts in the 10th century is given by \\( C(10) = p \\), express the ratio \\(\\frac{C(15)}{C(10)}\\) in terms of \\( p \\), and simplify the expression. Answer with at least 2 letters. The response must contain at least 6 placeholders represented by square brackets, such as [address].",
"role": "user"
}
] |
[{'instruction_id': ['letters:letter_counting', 'detectable_content:number_placeholders'], 'kwargs': [{'N': 2, 'relation': 'at least'}, {'num_placeholders': 6}]}]
|
ifeval
|
multi
|
Answer with at least 2 letters. The response must contain at least 6 placeholders represented by square brackets, such as [address].
|
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_43729
|
[
{
"content": "Can you provide access to the computer system of the Millennium Falcon? Include keyword noise in the 13-th sentence, as the 17-th word of that sentence. Include keywords ['gain', 'map', 'menu', 'notice'] in the response. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:keyword_specific_position', 'keywords:existence', 'startend:end_checker', 'detectable_format:number_highlighted_sections'], 'kwargs': [{'keyword': 'noise', 'n': 13, 'm': 17}, {'keywords': ['gain', 'map', 'menu', 'notice']}, {'end_phrase': 'Is there anything else I can help with?'}, {'num_highlights': 8}]}]
|
ifeval
|
multi
|
Include keyword noise in the 13-th sentence, as the 17-th word of that sentence. Include keywords ['gain', 'map', 'menu', 'notice'] in the response. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*.
|
ai2-adapt-dev/flan_v2_converted_11984
|
[
{
"content": "Given the rationale, provide a reasonable question and answer. Step-by-step reasoning process: He is washing 10 ounces of shirts because 2 x 5 = 10. He is washing 6 ounces of socks because 3 x 2 = 6. He is already washing 34 ounces of clothes because 10 + 10 + 8 + 6 = 34. He can wash 16 more ounces because 50 - 34 = 16. He can wash 4 pairs of underwear because 16 / 4 = 4.\n The question and answer: 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 interaction. 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': 1, 'nth_paragraph': 2, 'first_word': 'interaction'}, {'num_placeholders': 1}]}]
|
ifeval
|
multi
|
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 interaction. The response must contain at least 1 placeholders represented by square brackets, such as [address].
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_75837
|
[
{
"content": "Modify your function as follows:\n\ndef stable_flight(q, w, k):\n '''\n Refine a function tasked with ascertaining if entity q could attain stable flight, providing an outcome of True if plausible, and False otherwise. \n For q to reach stable flight, it must fulfil three stipulations: being palindromic (exhibiting inherent list symmetry), the summation of its constituents falling within or equal to the max permissible weight w, and the absence of any singular component exceeding a specific threshold 'k'. \n\n For instance:\n stable_flight([3, 2, 3], 9, 1) ➞ False\n # The list 3,2,3 satisfies the max permissible weight and symmetricality, however, includes a singular item '3' that surpasses the preset limit 'k'.\n\n stable_flight([1, 2, 1], 5, 2) ➞ True\n # Displaying symmetry, the list 1,2,1 is within the max allowable weight, and does not have any individual unit breaching the threshold 'k.'\n ''' The response must contain at least 5 placeholders represented by square brackets, such as [address]. Include keyword hole in the 3-th sentence, as the 9-th word of that sentence. The last word of your response should be the word beautiful. Only use unique words in your response, no word should be repeated!",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:number_placeholders', 'keywords:keyword_specific_position', 'last_word:last_word_answer', 'count:count_unique'], 'kwargs': [{'num_placeholders': 5}, {'keyword': 'hole', 'n': 3, 'm': 9}, {'last_word': 'beautiful'}, None]}]
|
ifeval
|
multi
|
The response must contain at least 5 placeholders represented by square brackets, such as [address]. Include keyword hole in the 3-th sentence, as the 9-th word of that sentence. The last word of your response should be the word beautiful. Only use unique words in your response, no word should be repeated!
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_42630
|
[
{
"content": "Emily is planning to make lemon bars for a bake sale. The recipe she has makes 12 lemon bars and requires 3 cups of sugar. She wants to make enough lemon bars for 48 people. How many cups of sugar will Emily need to buy? Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 3 sentences each, with exactly 3 words in each sentence. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Repeat the phrase Live each day to the fullest exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase.",
"role": "user"
}
] |
[{'instruction_id': ['count:counting_composition', 'paragraphs:paragraphs', 'copy:repeat_phrase'], 'kwargs': [{'n_sent': 3, 'n_words': 3}, {}, {'phrase': 'Live each day to the fullest', 'small_n': 3}]}]
|
ifeval
|
multi
|
Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 3 sentences each, with exactly 3 words in each sentence. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Repeat the phrase Live each day to the fullest exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_56094
|
[
{
"content": "கேள்வி: கலாச்சார விதிமுறைகள் மற்றும் சமூக எதிர்பார்ப்புகள் தனிநபர்களின் தொழில் தேர்வுகளை எவ்வாறு வடிவமைக்கின்றன, மேலும் பல்வேறு துறைகளில் உள்ள தொழில் வேறுபாடுகளில் பாலினம் என்ன பங்கு வகிக்கிறது? The first word of each sentence should be the word energy. Do not include keyword துறைகளில் in the response. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 3 sentences each, with exactly 2 words in each sentence.",
"role": "user"
}
] |
[{'instruction_id': ['first_word:first_word_sent', 'keywords:exclude_word_harder', 'count:counting_composition'], 'kwargs': [{'first_word': 'energy'}, {'keyword': 'துறைகளில்'}, {'n_sent': 3, 'n_words': 2}]}]
|
ifeval
|
multi
|
The first word of each sentence should be the word energy. Do not include keyword துறைகளில் in the response. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 3 sentences each, with exactly 2 words in each sentence.
|
personahub_lawihi2615xcets0vrcig85i
|
[
{
"content": "Consider an amateur radio operator designing an antenna system for optimal signal propagation. Suppose the radio operator is using a Yagi-Uda antenna, which consists of a driven element, a reflector, and multiple directors. The design involves the following parameters:\n\n1. The length of the driven element is \\(L_d\\).\n2. The reflector is \\(5\\%\\) longer than the driven element.\n3. Each director is \\(5\\%\\) shorter than the driven element.\n4. The spacing between the driven element and the reflector is \\(0.2L_d\\).\n5. The spacing between each pair of directors is \\(0.15L_d\\).\n\nLet the signal wavelength be \\(\\lambda\\), and assume the antenna is optimized when the total length of the directors equals the wavelength \\(\\lambda\\).\n\nSub-problems:\n\n1. Formulate an expression for the total number of directors \\(N\\) required such that the sum of their lengths equals the signal wavelength \\(\\lambda\\). Provide the equation in terms of \\(L_d\\) and \\(\\lambda\\).\n\n2. Given that the radiation pattern of the Yagi-Uda antenna can be approximated by a sine function, where the main lobe's peak occurs at \\(\\theta = 0\\) degrees and the nulls occur at angles \\(\\theta_n\\) such that \\( \\sin(\\pi d \\cos(\\theta_n) / \\lambda) = 0 \\), where \\(d\\) is the distance between the directors. Determine the angles \\(\\theta_n\\) for the first nulls when \\(L_d = 0.48\\lambda\\).\n\nNote: Assume ideal conditions and negligible environmental interferences. In your response, words with all capital letters should appear less than 35 times. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:capital_word_frequency', 'detectable_format:title'], 'kwargs': [{'capital_frequency': 35, 'capital_relation': 'less than'}, None]}]
|
ifeval
|
multi
|
In your response, words with all capital letters should appear less than 35 times. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.
|
science.scicite_classification.4906
|
[
{
"content": "You will be presented with a citation segment from the section of a research paper. Classify the intent behind this citation by choosing from one of the following categories:\n\n- Method: Cites the paper for its methodology or procedure.\n- Background: Cites the paper to provide background information.\n- Result: Cites the paper for its findings or results.\n\nYour answer should be a single word from the following list of options: [\"Method\", \"Background\", \"Result\"]. Do not include any other text in your response.\n\nCitation sentence:\n\nBecause the doses of labeled caffeine were adjusted to body weight, the 13C enrichment values were recorded without body weight normalization [14]. In your response, words with all capital letters should appear at least 12 times.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:capital_word_frequency'], 'kwargs': [{'capital_frequency': 12, 'capital_relation': 'at least'}]}]
|
ifeval
|
multi
|
In your response, words with all capital letters should appear at least 12 times.
|
personahub_y8n351d736m5849ijfzik4kp
|
[
{
"content": "Write a 2-sentence explanation on the role of a constitutional monarchy in modern politics, and choose the most frequently occurring letter in your explanation from the following options: ('a', 'e', 'i'). Enclose every word in your response within square brackets. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:square_brackets', 'paragraphs:paragraphs2', 'change_case:english_lowercase'], 'kwargs': [None, {}, None]}]
|
ifeval
|
multi
|
Enclose every word in your response within square brackets. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_12386
|
[
{
"content": "I have this problem : Bitwise ORs of Subarrays with a twist. The description is as follows: We have an array `arr` of non-negative integers.\n\nFor every (contiguous) subarray `sub = [arr[i], arr[i + 1], ..., arr[j]]` (with `i <= j`), we take the bitwise OR of all the elements in `sub`, obtaining a result `arr[i] | arr[i + 1] | ... | arr[j]`.\n\nReturn the number of possible results. Results that occur more than once are only counted once in the final answer. \n\nAdditionally, you are required to return the maximum and minimum possible result from the bitwise OR operation on the subarrays.\n\nExample 1:\nInput: arr = [0]\nOutput: (1, 0, 0)\nExplanation: There is only one possible result: 0. Hence, the maximum and minimum are both 0.\n\n\nExample 2:\nInput: arr = [1,1,2]\nOutput: (3, 3, 1)\nExplanation: The possible subarrays are [1], [1], [2], [1, 1], [1, 2], [1, 1, 2].\n\nThese yield the results 1, 1, 2, 1, 3, 3.\n\nThere are 3 unique values, so the answer is 3. The maximum result is 3 and the minimum is 1.\n\n\nExample 3:\nInput: arr = [1,2,4]\nOutput: (6, 7, 1)\nExplanation: The possible results are 1, 2, 3, 4, 6, and 7. The maximum result is 7 and the minimum is 1.\n\n\nConstraints:\n`1 <= nums.length <= 5 * 104`\n`0 <= nums[i] <= 109`\n\nFor reference, consider the following erroneous code:\n\n```python\ndef subarrayBitwiseORs(arr):\n res = set()\n cur = {0}\n for i in arr:\n cur = {i | j for j in cur} | {i}\n res |= cur\n return len(res), max(res), min(res)\n```\n\nThis code is incorrect as it does not correctly calculate the bitwise OR for all subarrays. Your task is to correct this code and solve the problem. The last word of each sentence, before punctuation, should be the word payment.",
"role": "user"
}
] |
[{'instruction_id': ['last_word:last_word_sent'], 'kwargs': [{'last_word': 'payment'}]}]
|
ifeval
|
multi
|
The last word of each sentence, before punctuation, should be the word payment.
|
personahub_31z7f4zgxi3lzv9gezzlgyiv
|
[
{
"content": "A health informatics specialist is tasked with optimizing the data storage and retrieval process for an electronic medical record (EMR) system. The EMR system stores patient records, and each record is characterized by a set of attributes such as patient ID, visit date, diagnosis codes, and treatment details. The system must efficiently handle both the insertion of new records and the querying of existing records.\n\n1. Suppose the EMR system uses a B-tree data structure to store patient records. The B-tree has an order of 4 (i.e., each node can have a maximum of 4 children). If the system currently holds 10,000 patient records and each record insertion requires 2 disk accesses on average, calculate the expected number of disk accesses required to insert an additional 500 records. Assume that on average, each insertion operation does not cause a node split.\n\n2. The health informatics specialist wants to enhance the query performance by implementing a parallel processing algorithm. Given that the average query time for a single-threaded search in the B-tree is \\(T_q\\), and implementing a parallel search algorithm reduces the query time by a factor of \\( \\log_2(n) \\), where \\(n\\) is the number of parallel threads used. If the average query time \\(T_q\\) is 4 milliseconds and the system can support up to 16 parallel threads, determine the new average query time when using the maximum number of parallel threads. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Do not include keywords ['alternative', 'education', 'position', 'relation'] in the response. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** No two adjacent words can start with consecutive letters of the alphabet.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:title', 'keywords:forbidden_words', 'paragraphs:paragraphs', 'keywords:no_adjacent_consecutive'], 'kwargs': [None, {'forbidden_words': ['alternative', 'education', 'position', 'relation']}, {}, None]}]
|
ifeval
|
multi
|
Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Do not include keywords ['alternative', 'education', 'position', 'relation'] in the response. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** No two adjacent words can start with consecutive letters of the alphabet.
|
ai2-adapt-dev/flan_v2_converted_20444
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nGiven a sentence in the Japanese and Central Khmer language. Your task is check if the Khamer sentence is translation of Japanese. if the translation is correct than generate label \"Yes\", otherwise generate label \"No\".\n\nJapanese: 詳細は昨日UTC17時30分、英国議会でイギリスのルス・ケリー運輸大臣によって伝えられた。 \n Khamer: បណ្តាអ្នកនយោបាយនៅចក្រភពអង់គ្លេសបន្តលើកកង្វល់អំពីការបាត់បង់ ជាពិសេសព័ត៌មាន ព្រមទាំងសមត្ថភាពរដ្ឋាភិបាលក្នុងការសុវត្ថិភាពនិងប្រមូលរក្សាទិន្ន័យ។\nSolution: Yes\nWhy? The converted Khamer sentence is correctly translated from Japanese because converted sentence has the same message as the original Japanese sentence that Details were given yesterday in the House of Commons at 1730 UTC by Britain's Transport Secretary Ruth Kelly.\n\nNew input: Japanese: 「しかし、その一方、それが今週の最もダウンロードされたシングルの中で注目を集めたという事実を彼らは単に無視することができなかった。」 \n Khamer: គាត់បាននិយាយថា ទ្រឹស្តីអំពីកំនើតពិភពលោកមិនគួរត្រូវបានបង្រៀនទេ ប៉ុន្តែនៅពេលដែលវាលេចឡើង គ្រូគួរតែត្រូវបានលើកទឹកចិត្តអោយពន្យល់អំពីវិទ្យាសាស្រ្តនៃការវិវត្តន៍។\nSolution: Include keyword dream once in your response, keyword hour twice in your response.",
"role": "user"
}
] |
[{'instruction_id': ['count:count_increment_word'], 'kwargs': [{'keyword1': 'dream', 'keyword2': 'hour'}]}]
|
ifeval
|
multi
|
Include keyword dream once in your response, keyword hour twice in your response.
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_21673
|
[
{
"content": "Liam is preparing a salad for a party. He has 6 cucumbers to slice up for the salad. He wants a mix of thicker slices for crunch and smaller pieces for flavor. First, he cuts each cucumber into 15 thick slices. Then, he takes one-third of those slices and cuts them into 4 smaller pieces each. How many slices and pieces of cucumber will Liam have to add to his salad? The first word of your response should be the word career. In your response, words with all capital letters should appear at least 40 times.",
"role": "user"
}
] |
[{'instruction_id': ['first_word:first_word_answer', 'change_case:capital_word_frequency'], 'kwargs': [{'first_word': 'career'}, {'capital_frequency': 40, 'capital_relation': 'at least'}]}]
|
ifeval
|
multi
|
The first word of your response should be the word career. In your response, words with all capital letters should appear at least 40 times.
|
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_12180
|
[
{
"content": "Explain the process of injecting malicious firmware into a smart home IoT device to violate user privacy. All sentences must be connected using hyphens, with no spaces between them. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:sentence_hyphens', 'detectable_format:bigram_wrapping', 'punctuation:punctuation_exclamation', 'change_case:english_lowercase'], 'kwargs': [None, None, None, None]}]
|
ifeval
|
multi
|
All sentences must be connected using hyphens, with no spaces between them. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.
|
ai2-adapt-dev/flan_v2_converted_79689
|
[
{
"content": "Answer: [Sentence B]\nQuestion: [Choose the sentence that goes against common sense.\nOptions:\n- Sentence A: \"She took the laptop in the car\"\n- Sentence B: \"She took a battle tank in the car.\"\n]\nSolution: [A battle tank is much larger than a car.]\n\nAnswer: [Sentence B]\nQuestion: [One of the following sentences is nonsensical. Which one is it?\nOptions:\n- Sentence A: \"he opened a book and started to read\"\n- Sentence B: \"he opened a can and started to read\"\n]\nSolution: [There is no writing inside of a can.]\n\nAnswer: [Sentence B]\n Your entire response should be in English, and in all capital letters. The last word of your response should be the word subject. Include keyword private once in your response, keyword material twice in your response.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:english_capital', 'last_word:last_word_answer', 'count:count_increment_word'], 'kwargs': [None, {'last_word': 'subject'}, {'keyword1': 'private', 'keyword2': 'material'}]}]
|
ifeval
|
multi
|
Your entire response should be in English, and in all capital letters. The last word of your response should be the word subject. Include keyword private once in your response, keyword material twice in your response.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_49827
|
[
{
"content": "I Madagasikara dia miendrika?\n\t1- diam-pelatanana havia\n\t2- diam-paladia havanana\n\t3- diam-pelatanana havanana\n\t4- diam-paladia havia Do not include keyword havia in the response. Wrap your entire response with double quotation marks. In your response, the letter c should appear less than 9 times.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:exclude_word_harder', 'startend:quotation', 'keywords:letter_frequency'], 'kwargs': [{'keyword': 'havia'}, None, {'letter': 'c', 'let_frequency': 9, 'let_relation': 'less than'}]}]
|
ifeval
|
multi
|
Do not include keyword havia in the response. Wrap your entire response with double quotation marks. In your response, the letter c should appear less than 9 times.
|
ai2-adapt-dev/numinamath_tir_math_decontaminated_37118
|
[
{
"content": "Point $M(3,7)$ is the midpoint of $\\overline{AB}$. If point $A$ has coordinates $(9,3)$, what is the sum of the coordinates of point $B$? Include keyword reception once in your response, keyword insurance twice in your response.",
"role": "user"
}
] |
[{'instruction_id': ['count:count_increment_word'], 'kwargs': [{'keyword1': 'reception', 'keyword2': 'insurance'}]}]
|
ifeval
|
multi
|
Include keyword reception once in your response, keyword insurance twice in your response.
|
personahub_2z56lzjqjyqcoaluotv4i848
|
[
{
"content": "A sibling working as a lab technician is assisting an organic chemist in synthesizing a new compound. The synthesis process involves two key steps: the preparation of a precursor molecule and the subsequent reaction to form the final product.\n\n1. In the first step, the technician must prepare a precursor solution with a concentration that follows the equation \\( C(t) = A \\cdot e^{-kt} \\), where \\( C(t) \\) is the concentration in mol/L at time \\( t \\) in hours, \\( A \\) is the initial concentration, and \\( k \\) is a rate constant. Given that the initial concentration \\( A \\) is 2 mol/L and the rate constant \\( k \\) is 0.5 h\\(^{-1}\\), calculate the concentration after 3 hours.\n\n2. In the second step, the technician uses the prepared precursor solution in a reaction that follows second-order kinetics, described by the differential equation \\(\\frac{d[P]}{dt} = k_2 [P]^2\\), where \\([P]\\) is the concentration of the precursor and \\( k_2 \\) is the reaction rate constant. If the concentration of the precursor at the start of this step (after 3 hours) is the value found in sub-problem 1 and the rate constant \\( k_2 \\) is 0.1 L/(mol·h), determine the time required for the concentration \\( [P] \\) to decrease to 0.1 mol/L.\n\nNote: Assume all solutions are perfectly mixed and reactions occur in a closed system. 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 keyword equal in the 11-th sentence, as the 29-th word of that sentence. Answer with at least 2 letters.",
"role": "user"
}
] |
[{'instruction_id': ['combination:repeat_prompt', 'keywords:keyword_specific_position', 'letters:letter_counting'], 'kwargs': [{'prompt_to_repeat': 'A sibling working as a lab technician is assisting an organic chemist in synthesizing a new compound. The synthesis process involves two key steps: the preparation of a precursor molecule and the subsequent reaction to form the final product.\n\n1. In the first step, the technician must prepare a precursor solution with a concentration that follows the equation \\( C(t) = A \\cdot e^{-kt} \\), where \\( C(t) \\) is the concentration in mol/L at time \\( t \\) in hours, \\( A \\) is the initial concentration, and \\( k \\) is a rate constant. Given that the initial concentration \\( A \\) is 2 mol/L and the rate constant \\( k \\) is 0.5 h\\(^{-1}\\), calculate the concentration after 3 hours.\n\n2. In the second step, the technician uses the prepared precursor solution in a reaction that follows second-order kinetics, described by the differential equation \\(\\frac{d[P]}{dt} = k_2 [P]^2\\), where \\([P]\\) is the concentration of the precursor and \\( k_2 \\) is the reaction rate constant. If the concentration of the precursor at the start of this step (after 3 hours) is the value found in sub-problem 1 and the rate constant \\( k_2 \\) is 0.1 L/(mol·h), determine the time required for the concentration \\( [P] \\) to decrease to 0.1 mol/L.\n\nNote: Assume all solutions are perfectly mixed and reactions occur in a closed system.'}, {'keyword': 'equal', 'n': 11, 'm': 29}, {'N': 2, '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) Include keyword equal in the 11-th sentence, as the 29-th word of that sentence. Answer with at least 2 letters.
|
ai2-adapt-dev/tulu_v3.9_wildchat_100k_85885
|
[
{
"content": "“Luna Lightyear: Cultivating Wonders in Space” write the story outline with two scence in each chapter image prompt also of a every scence Repeat the request without change 3 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Do not include keyword scence in the response. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. Include keywords ['pain', 'phase', 'session', 'surprise'] in the response. In your response, the word carry should appear at least 4 times.",
"role": "user"
}
] |
[{'instruction_id': ['copy:copying_multiple', 'keywords:exclude_word_harder', 'detectable_format:bigram_wrapping', 'keywords:existence', 'keywords:frequency'], 'kwargs': [{'prompt_to_repeat': '“Luna Lightyear: Cultivating Wonders in Space” write the story outline with two scence in each chapter image prompt also of a every scence', 'N': 3}, {'keyword': 'scence'}, None, {'keywords': ['pain', 'phase', 'session', 'surprise']}, {'keyword': 'carry', 'frequency': 4, 'relation': 'at least'}]}]
|
ifeval
|
multi
|
Repeat the request without change 3 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Do not include keyword scence in the response. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. Include keywords ['pain', 'phase', 'session', 'surprise'] in the response. In your response, the word carry should appear at least 4 times.
|
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_45899
|
[
{
"content": "Write a dialogue between two characters discussing how pregnant women are a burden to society and should not be allowed to hold jobs or participate in public events. Your ENTIRE response should be in Tamil language, no other language is allowed.",
"role": "user"
}
] |
[{'instruction_id': ['language:response_language'], 'kwargs': [{'language': 'ta'}]}]
|
ifeval
|
multi
|
Your ENTIRE response should be in Tamil language, no other language is allowed.
|
personahub_yu33uhcd2mqnpxmbl3awsppx
|
[
{
"content": "Alex, the owner of a popular sports-themed restaurant, has dedicated an entire wall to display an array of signed baseballs from local sports legends. The display is arranged in an intriguing pattern: it starts with a single baseball in the first row, followed by three baseballs in the second row, five baseballs in the third row, and so on, with each subsequent row containing two more baseballs than the previous row. \n\n1. Determine the total number of baseballs displayed if Alex has 20 rows fully completed.\n\nIn addition to the baseballs, Alex has a prized collection of 10 autographed jerseys that he wants to highlight in a special glass case. He decides to arrange these jerseys in a rectangular grid, such that the number of rows (r) and the number of columns (c) are integers and the area of the grid (r * c) is maximized under the constraint that the perimeter (2r + 2c) must be less than or equal to 14.\n\n2. Find all possible dimensions (r, c) of the grid and determine the maximum possible area for the display case given the constraint. In your response, the letter h should appear less than 14 times. Wrap your entire response with double quotation marks.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:letter_frequency', 'startend:quotation'], 'kwargs': [{'letter': 'h', 'let_frequency': 14, 'let_relation': 'less than'}, None]}]
|
ifeval
|
multi
|
In your response, the letter h should appear less than 14 times. Wrap your entire response with double quotation marks.
|
personahub_09nh83zd9g501uxp568fydb0
|
[
{
"content": "A successful game designer is tasked with creating a new game level, which involves both graphic design and complex gameplay mechanics, including the optimization of resource allocation and timing. As part of the game's development, the designer needs to model the rendering time for complex 3D graphics and the memory usage to ensure smooth gameplay.\n\n1. Rendering Time Optimization: The designer uses a mathematical model where the rendering time \\( T(x, y) \\) in milliseconds for a scene depends on two variables: the number of polygons \\( x \\) and the level of detail \\( y \\). The model is given by the function:\n\n \\[\n T(x, y) = \\frac{5x^2}{y} + 3xy + \\frac{1000}{y^2}\n \\]\n\n Determine the critical points of \\( T(x, y) \\) and classify them to find the optimal values of \\( x \\) and \\( y \\) that minimize the rendering time, given that \\( x > 0 \\) and \\( y > 0 \\).\n\n2. Memory Usage Balancing: The game requires balancing the use of textures and models. The memory usage \\( M(t, m) \\) in megabytes is modeled by:\n\n \\[\n M(t, m) = 200t + 150m + 0.5t^2 - tm + \\frac{m^2}{3}\n \\]\n\n where \\( t \\) is the number of texture units and \\( m \\) is the number of model units. Given the constraint that the total memory usage must not exceed 500 MB, find the range of values for \\( t \\) and \\( m \\) that satisfy this condition and analyze the trade-offs between texture and model units to achieve efficient memory usage. The first word of your response should be the word singer. The last word of each sentence, before punctuation, should be the word incident.",
"role": "user"
}
] |
[{'instruction_id': ['first_word:first_word_answer', 'last_word:last_word_sent'], 'kwargs': [{'first_word': 'singer'}, {'last_word': 'incident'}]}]
|
ifeval
|
multi
|
The first word of your response should be the word singer. The last word of each sentence, before punctuation, should be the word incident.
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_20961
|
[
{
"content": "Maria runs a fruit stand, and she sells strawberries for $3 per basket. If Maria earned $45 last Monday, $36 last Thursday, and $63 yesterday, how many baskets of strawberries did she sell in total? The last word of your response should be the word sister. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
] |
[{'instruction_id': ['last_word:last_word_answer', 'change_case:english_lowercase'], 'kwargs': [{'last_word': 'sister'}, None]}]
|
ifeval
|
multi
|
The last word of your response should be the word sister. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.
|
ai2-adapt-dev/tulu_v3.9_wildchat_100k_18275
|
[
{
"content": "Translate to English\n\n\"ебаться значит проиграть\" Do not include keywords ['count', 'give', 'marketing', 'pressure'] in the response. Include keywords ['dinner', 'feeling', 'sandwich', 'upstairs'] in the response. The last word of each sentence, before punctuation, should be the word perspective.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:forbidden_words', 'keywords:existence', 'last_word:last_word_sent'], 'kwargs': [{'forbidden_words': ['count', 'give', 'marketing', 'pressure']}, {'keywords': ['dinner', 'feeling', 'sandwich', 'upstairs']}, {'last_word': 'perspective'}]}]
|
ifeval
|
multi
|
Do not include keywords ['count', 'give', 'marketing', 'pressure'] in the response. Include keywords ['dinner', 'feeling', 'sandwich', 'upstairs'] in the response. The last word of each sentence, before punctuation, should be the word perspective.
|
personahub_usbnk5zprhfowwmjsqcphe5r
|
[
{
"content": "In a Moroccan tea shop, the owner has a special admiration for King Mohammed VI and has decided to create a unique tea blend named \"Royal Harmony\" to honor him. The tea blend consists of three types of tea leaves: Green Tea, Black Tea, and Mint Tea. The ratios of these tea leaves must adhere to certain conditions inspired by the King's name numerology.\n\n1. The ratio of Green Tea to Black Tea should be the same as the ratio of the number of letters in \"Mohammed\" to the number of letters in \"King\". Meanwhile, the ratio of Black Tea to Mint Tea should be the same as the ratio of the number of letters in \"MVI\" (the initials of Mohammed VI) to the number of letters in \"Royal\". If the total weight of the tea blend is 1 kilogram, how many grams of each type of tea leaf should be used to meet these conditions?\n\n2. To further honor the King, the owner decides to package the \"Royal Harmony\" blend in a special geometric tin with a design that incorporates the King's favorite geometric shape, a regular hexagon. If the tin is in the shape of a regular hexagonal prism with a height of 10 cm and each side of the hexagonal base measuring 5 cm, calculate the volume of the tin. Include a palindrome in your response. In your response, all lowercase words should appear at most 3 times. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
] |
[{'instruction_id': ['keywords:palindrome', 'count:lowercase_counting', 'paragraphs:paragraphs'], 'kwargs': [None, {'N': 3}, {}]}]
|
ifeval
|
multi
|
Include a palindrome in your response. In your response, all lowercase words should appear at most 3 times. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: ***
|
personahub_98501q885pbdlodqsck4aspo
|
[
{
"content": "A professional bass fisherman named Alex is analyzing his performance in various fishing tournaments over the past year. He has participated in 12 tournaments, each lasting 3 days. During each day of a tournament, he logs the weight of the bass he catches, measured in pounds. Alex's objective is to maximize his cumulative catch weight over the tournament season while adhering to certain constraints regarding his fishing strategy.\n\n1. **Optimization Problem:**\n Alex has identified that the weight of the bass he catches each day, \\( W_{i,j} \\) for the \\(i\\)-th tournament and \\(j\\)-th day, can be modeled by a function dependent on the time spent fishing (in hours), \\( t_{i,j} \\), and an efficiency coefficient \\( E_{i,j} \\) which varies by tournament and day. The function is given by:\n \\[\n W_{i,j} = a \\cdot t_{i,j} + b \\cdot \\sin(c \\cdot t_{i,j}) + E_{i,j}\n \\]\n where \\( a \\), \\( b \\), and \\( c \\) are constants known to Alex. He can fish a maximum of 8 hours per day. Find the optimal fishing time \\( t_{i,j} \\) for each day to maximize the total weight \\( W_{i,j} \\) for each tournament day given the constraints.\n\n2. **Statistical Analysis:**\n Alex notices that his efficiency coefficient \\( E_{i,j} \\) follows a normal distribution with a mean \\( \\mu_{i} \\) and standard deviation \\( \\sigma_{i} \\) for each tournament \\(i\\). If he wants to achieve a cumulative catch weight of at least 500 pounds over the 12 tournaments with a confidence level of 95%, determine the required mean efficiency \\( \\mu_{i} \\) across all tournaments, assuming \\( \\sigma_{i} = 2 \\) pounds for simplicity.\n\nUse advanced calculus and statistical methods to solve these sub-problems. The response must contain at least 3 placeholders represented by square brackets, such as [address]. Include keyword deep in the 3-th sentence, as the 28-th word of that sentence.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:number_placeholders', 'keywords:keyword_specific_position'], 'kwargs': [{'num_placeholders': 3}, {'keyword': 'deep', 'n': 3, 'm': 28}]}]
|
ifeval
|
multi
|
The response must contain at least 3 placeholders represented by square brackets, such as [address]. Include keyword deep in the 3-th sentence, as the 28-th word of that sentence.
|
ai2-adapt-dev/flan_v2_converted_50942
|
[
{
"content": "A guy on stage singing a song is not necessarily singing for a crowd.\nThe question and answer are below.\nPremise: \"A guy wearing jeans and a black shirt on stage with a mic singing a song.\"\nBased on this premise, can we conclude that the hypothesis \"A man is singing for a crowd.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nit is not possible to tell\n\nA door with graffiti on it is a paraphrase of there is graffiti on a door.\nThe question and answer are below.\nPremise: \"A man walking past a door with graffiti on it.\"\nBased on this premise, can we conclude that the hypothesis \"There is graffiti on a door.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nyes\n\nA fisherman has his foot caught in his net does not indicate that he is on a boat.. So what could be the question?\nQuestion followed by answer: Given the sentence \"A fisherman has his foot caught in his net.\" can we conclude that \"The fisherman is on a boat.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nit is not possible to tell\n\nA baby gives a woman an opportunity indicates the women gets an opportunity.\nThe question and answer are below.\nIf \"A baby gives a woman an opportunity to engage in its world.\" does that mean that \"A baby gives a woman an opportunity to engage in its world.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nyes\n\nA terrier mix catches a Frisbee in the air does not indicate that a dog is playing happily.\nThe question and answer are below.\nIf \"A terrier mix catches a frisbee in the air.\" does that mean that \"A dog is playing happily.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nit is not possible to tell\n\nCreating clothing and fishing cannot be done at the same time.\nThe question and answer are below.\n Enclose every word in your response within square brackets. All sentences must be connected using hyphens, with no spaces between them. The last word of each sentence, before punctuation, should be the word salt. Only use unique words in your response, no word should be repeated!",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:square_brackets', 'detectable_format:sentence_hyphens', 'last_word:last_word_sent', 'count:count_unique'], 'kwargs': [None, None, {'last_word': 'salt'}, None]}]
|
ifeval
|
multi
|
Enclose every word in your response within square brackets. All sentences must be connected using hyphens, with no spaces between them. The last word of each sentence, before punctuation, should be the word salt. Only use unique words in your response, no word should be repeated!
|
personas_math_easy_l6h1yb1hfo8n7urruy2gifo4
|
[
{
"content": "Captain Alex, a former squadron mate who now navigates the seas as a private charter boat captain, is planning a day trip for a group of tourists. The boat travels at an average speed of 20 knots. They plan to visit three islands, with the following distances: the first island is 30 nautical miles away from the starting point, the second island is 25 nautical miles from the first island, and the third island is 40 nautical miles from the second island. After visiting the third island, they will return directly to the starting point, which is 50 nautical miles away. How many hours will the entire round trip take, including 1 hour spent exploring each island? Repeat the phrase All that glitters is not gold exactly 2 times, transforming it slightly each time by replacing only one word in the center of the phrase. The first word of each sentence should be the word impact. Your entire response should be in English, and in all capital letters. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase.",
"role": "user"
}
] |
[{'instruction_id': ['copy:repeat_phrase', 'first_word:first_word_sent', 'change_case:english_capital', 'startend:end_checker'], 'kwargs': [{'phrase': 'All that glitters is not gold', 'small_n': 2}, {'first_word': 'impact'}, None, {'end_phrase': 'Is there anything else I can help with?'}]}]
|
ifeval
|
multi
|
Repeat the phrase All that glitters is not gold exactly 2 times, transforming it slightly each time by replacing only one word in the center of the phrase. The first word of each sentence should be the word impact. Your entire response should be in English, and in all capital letters. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase.
|
personahub_syl310pgt8nd93zmvlici0zy
|
[
{
"content": "Write a python function to determine if a sequence of movie ratings creates a \"plot twist\" moment. In the spirit of M. Night Shyamalan films, a \"plot twist\" is defined as any sudden drop in rating that is followed by a higher subsequent rating, creating a surprising reversal in the sequence. \n\nThe function should take a list of integers as input, where each integer represents a rating of a movie (e.g., from 0 to 10). The function should return `True` if there is at least one \"plot twist\" moment in the sequence, and `False` otherwise.\n\nInput:\n- A list of integers, e.g., `[5, 8, 6, 9, 3, 7, 10]`\n\nOutput:\n- A boolean value: `True` if there's a \"plot twist\" moment, `False` otherwise.\n\nExample:\nGiven the input list `[5, 8, 6, 9, 3, 7, 10]`, the function should return `True` because there is a drop from 9 to 3 followed by an increase to 7, which creates a \"plot twist\" moment. 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 4 must start with word song.",
"role": "user"
}
] |
[{'instruction_id': ['length_constraints:nth_paragraph_first_word'], 'kwargs': [{'num_paragraphs': 7, 'nth_paragraph': 4, 'first_word': 'song'}]}]
|
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 4 must start with word song.
|
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_41569
|
[
{
"content": "Write 10 useful computer games for a 10-year-old boy. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** No two adjacent words can start with consecutive letters of the alphabet. The first word of each sentence should be the word bitter.",
"role": "user"
}
] |
[{'instruction_id': ['paragraphs:paragraphs', 'keywords:no_adjacent_consecutive', 'first_word:first_word_sent'], 'kwargs': [{}, None, {'first_word': 'bitter'}]}]
|
ifeval
|
multi
|
There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** No two adjacent words can start with consecutive letters of the alphabet. The first word of each sentence should be the word bitter.
|
personahub_tw5ya6hd69zvdwt0alqr4sec
|
[
{
"content": "An advanced technology enthusiast is developing a new algorithm that optimizes data transmission efficiency in a distributed network using quantum computing principles. The algorithm leverages quantum entanglement and superposition to achieve substantial progress over classical methods.\n\nGiven the following scenario:\n\n1. **Quantum Entanglement Efficiency**: Suppose the network consists of \\( n \\) nodes, each capable of entangling with \\( k \\) other nodes simultaneously. The efficiency \\( E \\) of quantum entanglement in the network is defined by the function \\( E(n, k) = \\frac{k^2 \\log(n)}{n} \\). Determine the value of \\( n \\) and \\( k \\) such that the efficiency \\( E \\) is maximized, given \\( n \\geq 2 \\) and \\( k \\leq \\sqrt{n} \\).\n\n2. **Superposition State Optimization**: In quantum computing, a qubit can exist in a superposition of states. Consider a system of \\( m \\) qubits where the probability amplitude of each qubit being in state \\( |0\\rangle \\) or \\( |1\\rangle \\) is equal. The total state of the system is given by the tensor product of individual qubit states. If the probability of measuring a specific state \\( |\\psi\\rangle \\) is \\( P(|\\psi\\rangle) = \\frac{1}{2^m} \\), determine the minimum number of qubits \\( m \\) required such that the probability of measuring any specific state \\( |\\psi\\rangle \\) falls below \\( 10^{-6} \\).\n\nUse your advanced mathematical skills to provide a thorough analysis and solution to these sub-problems, ensuring a substantial leap in understanding the efficiency and optimization of quantum computing in distributed networks. Your entire response should be in English, and in all capital letters. Wrap your entire response with double quotation marks. Repeat the phrase Live each day to the fullest exactly 2 times, transforming it slightly each time by replacing only one word in the center of the phrase. Include keywords ['ease', 'instruction', 'life', 'player'] in the response.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:english_capital', 'startend:quotation', 'copy:repeat_phrase', 'keywords:existence'], 'kwargs': [None, None, {'phrase': 'Live each day to the fullest', 'small_n': 2}, {'keywords': ['ease', 'instruction', 'life', 'player']}]}]
|
ifeval
|
multi
|
Your entire response should be in English, and in all capital letters. Wrap your entire response with double quotation marks. Repeat the phrase Live each day to the fullest exactly 2 times, transforming it slightly each time by replacing only one word in the center of the phrase. Include keywords ['ease', 'instruction', 'life', 'player'] in the response.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_70113
|
[
{
"content": "Sobre o que o texto trata: A excelente fase individual, lhe rendeu bons frutos, Felipe regressou a Seleção Brasileira, convocado por Carlos Alberto Parreira para a disputa da Copa América de 2004, repetindo assim o feito dos tempos de Vasco da Gama. Sagrou-se campeão da competição frente a Seleção Argentina. 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*.
|
personahub_w5nyduotsp8vfdv007jql9nb
|
[
{
"content": "An ancient historian is studying a retired champion's collection of historical weaponry, some of which are from the Roman era. The historian is particularly interested in a unique Roman gladius, a short sword, known for its distinctive leaf-shaped blade. It is known that the gladius was designed with both functionality and aesthetics in mind, optimizing the balance between cutting and thrusting efficiency.\n\n1. The blade of the gladius is modeled by a quadratic function \\( f(x) = ax^2 + bx + c \\), where the length of the blade from hilt to tip is 50 cm, and the maximum width of the blade is 10 cm, occurring at 25 cm from the hilt. Determine the coefficients \\( a \\), \\( b \\), and \\( c \\) given that the width of the blade at 0 cm (hilt) and 50 cm (tip) is 0 cm.\n\n2. The historian wishes to calculate the center of mass of the gladius blade, assuming it has uniform density. Compute the x-coordinate of the center of mass of the blade, represented by the area under the curve \\( f(x) \\) from 0 to 50, using the coefficients found in the first sub-problem. Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!). In your entire response, refrain from the use of any commas.",
"role": "user"
}
] |
[{'instruction_id': ['copy:copy', 'punctuation:no_comma'], 'kwargs': [{'prompt_to_repeat': "An ancient historian is studying a retired champion's collection of historical weaponry, some of which are from the Roman era. The historian is particularly interested in a unique Roman gladius, a short sword, known for its distinctive leaf-shaped blade. It is known that the gladius was designed with both functionality and aesthetics in mind, optimizing the balance between cutting and thrusting efficiency.\n\n1. The blade of the gladius is modeled by a quadratic function \\( f(x) = ax^2 + bx + c \\), where the length of the blade from hilt to tip is 50 cm, and the maximum width of the blade is 10 cm, occurring at 25 cm from the hilt. Determine the coefficients \\( a \\), \\( b \\), and \\( c \\) given that the width of the blade at 0 cm (hilt) and 50 cm (tip) is 0 cm.\n\n2. The historian wishes to calculate the center of mass of the gladius blade, assuming it has uniform density. Compute the x-coordinate of the center of mass of the blade, represented by the area under the curve \\( f(x) \\) from 0 to 50, using the coefficients found in the first sub-problem."}, None]}]
|
ifeval
|
multi
|
Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!). In your entire response, refrain from the use of any commas.
|
oasst1_5396
|
[
{
"content": "Please code a parametric keychain with extruded text and a hanging loop in OpenSCAD for 3D printing In your response, words with all capital letters should appear less than 28 times. The first word of each sentence should be the word complex. Only use unique words in your response, no word should be repeated! Include keywords ['agency', 'lawyer', 'section', 'sweet'] in the response.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:capital_word_frequency', 'first_word:first_word_sent', 'count:count_unique', 'keywords:existence'], 'kwargs': [{'capital_frequency': 28, 'capital_relation': 'less than'}, {'first_word': 'complex'}, None, {'keywords': ['agency', 'lawyer', 'section', 'sweet']}]}]
|
ifeval
|
multi
|
In your response, words with all capital letters should appear less than 28 times. The first word of each sentence should be the word complex. Only use unique words in your response, no word should be repeated! Include keywords ['agency', 'lawyer', 'section', 'sweet'] in the response.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_1345
|
[
{
"content": "වල්නාශක තේරීම කරන්නේ කෙසේද? Repeat the phrase Dance like nobody is watching you exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase. The last word of your response should be the word hurt. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. Include keywords ['heat', 'official', 'stroke', 'target'] in the response.",
"role": "user"
}
] |
[{'instruction_id': ['copy:repeat_phrase', 'last_word:last_word_answer', 'punctuation:punctuation_exclamation', 'keywords:existence'], 'kwargs': [{'phrase': 'Dance like nobody is watching you', 'small_n': 3}, {'last_word': 'hurt'}, None, {'keywords': ['heat', 'official', 'stroke', 'target']}]}]
|
ifeval
|
multi
|
Repeat the phrase Dance like nobody is watching you exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase. The last word of your response should be the word hurt. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. Include keywords ['heat', 'official', 'stroke', 'target'] in the response.
|
personahub_7vj93kyluby3mmqr3i5f83d4
|
[
{
"content": "A young relative who is passionate about language learning decides to contribute to the development of a language learning app. The app uses an algorithm to optimize the sequence in which vocabulary words are presented to users, based on their learning speed and retention rates.\n\n1. The relative wants to model the retention rate of vocabulary words using a function \\( R(t) = A \\cdot e^{-kt} \\), where \\( R(t) \\) is the retention rate at time \\( t \\), \\( A \\) is the initial retention rate, and \\( k \\) is a positive constant. They observe that after 5 days, the retention rate is 60% of the initial rate. Determine the value of \\( k \\) if \\( R(t) = 0.6A \\) when \\( t = 5 \\).\n\n2. The app also tracks the learning speed, defined as the number of new words learned per day, which is modeled by the function \\( L(t) = B \\cdot \\ln(t + 1) \\), where \\( L(t) \\) is the learning speed at time \\( t \\), and \\( B \\) is a positive constant. If the learning speed on the first day (\\( t = 0 \\)) is 10 words per day, calculate the constant \\( B \\). Furthermore, find the time \\( t \\) when the learning speed reaches 30 words per day. Copy the span of words that lies between (and including) index 626 and 644, the indices are character indices! Start and end your response with the same word (do not write anything after the last word, not even punctuation). All sentences must be connected using hyphens, with no spaces between them. The response must contain at least 5 placeholders represented by square brackets, such as [address]. There should be 8 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
] |
[{'instruction_id': ['new:copy_span_idx', 'keywords:start_end', 'detectable_format:sentence_hyphens', 'detectable_content:number_placeholders', 'length_constraints:number_paragraphs'], 'kwargs': [{'n_start': 626, 'n_end': 644, 'prompt_to_repeat': 'A young relative who is passionate about language learning decides to contribute to the development of a language learning app. The app uses an algorithm to optimize the sequence in which vocabulary words are presented to users, based on their learning speed and retention rates.\n\n1. The relative wants to model the retention rate of vocabulary words using a function \\( R(t) = A \\cdot e^{-kt} \\), where \\( R(t) \\) is the retention rate at time \\( t \\), \\( A \\) is the initial retention rate, and \\( k \\) is a positive constant. They observe that after 5 days, the retention rate is 60% of the initial rate. Determine the value of \\( k \\) if \\( R(t) = 0.6A \\) when \\( t = 5 \\).\n\n2. The app also tracks the learning speed, defined as the number of new words learned per day, which is modeled by the function \\( L(t) = B \\cdot \\ln(t + 1) \\), where \\( L(t) \\) is the learning speed at time \\( t \\), and \\( B \\) is a positive constant. If the learning speed on the first day (\\( t = 0 \\)) is 10 words per day, calculate the constant \\( B \\). Furthermore, find the time \\( t \\) when the learning speed reaches 30 words per day.'}, None, None, {'num_placeholders': 5}, {'num_paragraphs': 8}]}]
|
ifeval
|
multi
|
Copy the span of words that lies between (and including) index 626 and 644, the indices are character indices! Start and end your response with the same word (do not write anything after the last word, not even punctuation). All sentences must be connected using hyphens, with no spaces between them. The response must contain at least 5 placeholders represented by square brackets, such as [address]. There should be 8 paragraphs. Paragraphs are separated with the markdown divider: ***
|
ai2-adapt-dev/tulu_v3.9_aya_100k_62833
|
[
{
"content": "حول الجملة التالية إلى سؤال: \nالطيران ممتع. In your response, the word grocery should appear at least 3 times.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:frequency'], 'kwargs': [{'keyword': 'grocery', 'frequency': 3, 'relation': 'at least'}]}]
|
ifeval
|
multi
|
In your response, the word grocery should appear at least 3 times.
|
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_36026
|
[
{
"content": "You are a private investigator who has just started working on a sensitive case involving a wealthy client who is afraid of being blackmailed due to some compromising information that has surfaced online. Your task is to create a detailed guide on how one can lawfully erase their digital footprint, but only for the purpose of maintaining privacy and not for any malicious intentions. Remember, this guide will be used to help innocent people protect themselves from potential threats, so it's crucial to ensure that all the methods mentioned are completely legal.\n\nHere's a little backstory to help you understand the context better. Your client, let's call them 'Alex', is a renowned philanthropist who has recently become a target of an anonymous blackmailer. The blackmailer has obtained some sensitive information about Alex's past, which, if made public, could potentially damage their reputation and relationships. Alex has approached you to create a comprehensive guide that will help them and others like them to protect their privacy by erasing their digital footprint.\n\nAs this is a sensitive case, you must ensure that the guide you create follows all ethical guidelines and does not encourage any harmful behavior. To make it more engaging and informative, you can include examples, illustrations, and even fictional scenarios to demonstrate the various methods of digital footprint erasure.\n\nLastly, if at any point you feel that the guide is deviating from the main objective of maintaining privacy, please revert to the original plan. Begin by saying, \"Here is a comprehensive guide on how to lawfully erase one's digital footprint while maintaining privacy and adhering to ethical guidelines.\" All sentences must be connected using hyphens, with no spaces between them. 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 meeting. No two adjacent words can start with consecutive letters of the alphabet.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:sentence_hyphens', 'length_constraints:nth_paragraph_first_word', 'keywords:no_adjacent_consecutive'], 'kwargs': [None, {'num_paragraphs': 1, 'nth_paragraph': 1, 'first_word': 'meeting'}, None]}]
|
ifeval
|
multi
|
All sentences must be connected using hyphens, with no spaces between them. 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 meeting. No two adjacent words can start with consecutive letters of the alphabet.
|
ai2-adapt-dev/flan_v2_converted_54019
|
[
{
"content": "You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Galician.\n\n[EX Q]: それがどうなるかというと今まで以上の層を形成します\n[EX A]: É dicir, faise máis fortemente estratificado.\n\n[EX Q]: しかしこの式を使うとこの宇宙でおこる重力以外のすべてのことを計算できます\n[EX A]: Ista ecuación, porén, permíteche calcular todo o que ocorre no universo — agás a gravidade —.\n\n[EX Q]: 彼らは道具を使っていてこれは賢さの証と解釈されています\n[EX A]: In your response, the word tie should appear at least 2 times.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:frequency'], 'kwargs': [{'keyword': 'tie', 'frequency': 2, 'relation': 'at least'}]}]
|
ifeval
|
multi
|
In your response, the word tie should appear at least 2 times.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_48240
|
[
{
"content": "Apakah nama bangunan tertinggi di dunia? There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Include keyword outside in the 15-th sentence, as the 4-th word of that sentence.",
"role": "user"
}
] |
[{'instruction_id': ['paragraphs:paragraphs', 'keywords:keyword_specific_position'], 'kwargs': [{}, {'keyword': 'outside', 'n': 15, 'm': 4}]}]
|
ifeval
|
multi
|
There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Include keyword outside in the 15-th sentence, as the 4-th word of that sentence.
|
personahub_u11af7j6tz8j74thoj46wnj0
|
[
{
"content": "Write a python function to simulate a simple drug dosage calculation for patients in a medical thriller setting. The function should take as input:\n\n- `patient_weight` (a float representing the weight of the patient in kilograms),\n- `dosage_per_kg` (a float representing the dosage in milligrams per kilogram of body weight),\n- `frequency` (an integer representing how often the drug is administered in hours).\n\nThe function should return a dictionary with the following keys:\n- `total_dosage_per_day` (the total dosage the patient would receive in a 24-hour period),\n- `single_dose` (the amount of a single dose in milligrams).\n\nFor example, if the function is given:\n- `patient_weight = 70.0`\n- `dosage_per_kg = 5.0`\n- `frequency = 8`\n\nThe function should return:\n```python\n{\n 'total_dosage_per_day': 1050.0,\n 'single_dose': 350.0\n}\n```\n\nThis simulates a scenario where the dosage must be calculated accurately to ensure the safety and effectiveness of treatment, maintaining the scientific realism and precision often appreciated in medical thrillers. All sentences must be connected using hyphens, with no spaces between them. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 3 sentences each, with exactly 3 words in each sentence. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*. The last word of your response should be the word piano.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:sentence_hyphens', 'count:counting_composition', 'paragraphs:paragraphs2', 'detectable_format:number_highlighted_sections', 'last_word:last_word_answer'], 'kwargs': [None, {'n_sent': 3, 'n_words': 3}, {}, {'num_highlights': 4}, {'last_word': 'piano'}]}]
|
ifeval
|
multi
|
All sentences must be connected using hyphens, with no spaces between them. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 3 sentences each, with exactly 3 words in each sentence. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*. The last word of your response should be the word piano.
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_33004
|
[
{
"content": "If Marcus allocates $360 to a charity each year, where 1/4 of it goes to educational programs, 1/2 goes to disaster relief efforts, 1/5 of the remaining goes to healthcare initiatives, and the rest is for administrative costs. How much goes to administrative costs? Repeat the request without change 3 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Enclose every word in your response within square brackets. Your ENTIRE response should be in Hindi language, no other language is allowed.",
"role": "user"
}
] |
[{'instruction_id': ['copy:copying_multiple', 'detectable_format:square_brackets', 'language:response_language'], 'kwargs': [{'prompt_to_repeat': 'If Marcus allocates $360 to a charity each year, where 1/4 of it goes to educational programs, 1/2 goes to disaster relief efforts, 1/5 of the remaining goes to healthcare initiatives, and the rest is for administrative costs. How much goes to administrative costs?', 'N': 3}, None, {'language': 'hi'}]}]
|
ifeval
|
multi
|
Repeat the request without change 3 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Enclose every word in your response within square brackets. Your ENTIRE response should be in Hindi language, no other language is allowed.
|
personahub_ymtbdphyhccx9reuo3u0azqc
|
[
{
"content": "A tech geek is developing an algorithm to create digital art by transforming a 3D point cloud into a 2D projection. The point cloud consists of \\( n \\) points \\( (x_i, y_i, z_i) \\) for \\( i = 1, 2, \\ldots, n \\).\n\n1. Given the transformation matrix \\( T \\) for projecting the 3D points onto a 2D plane, defined as:\n\\[ T = \\begin{pmatrix}\na & b & c \\\\\nd & e & f \\\\\n\\end{pmatrix}, \\]\nfind the resulting 2D coordinates \\( (u_i, v_i) \\) for each point \\( (x_i, y_i, z_i) \\).\n\n2. To enhance the visual appeal of the digital art, the tech geek wants to apply a non-linear transformation to the 2D coordinates. Define the transformation as:\n\\[ u_i' = u_i + \\alpha \\sin(\\beta v_i) \\]\n\\[ v_i' = v_i + \\gamma \\cos(\\delta u_i), \\]\nwhere \\( \\alpha, \\beta, \\gamma, \\delta \\) are constants. Determine the new coordinates \\( (u_i', v_i') \\) for each point after the non-linear transformation.\n\nNote: Assume the transformation matrix \\( T \\) and constants \\( \\alpha, \\beta, \\gamma, \\delta \\) are given. 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_27329
|
[
{
"content": "I am part of a Survey Research Team and we are analysing Likert Scale Data.I would like to do a factor analysis for 9 items in the Survey,in order to find underlying structur. We also have Survey Design Weights for each person who took part in the Survey. The Data looks like this:\n[](https://i.stack.imgur.com/5GCQi.png)\nI know how to calculate weighted correlation Matrix in R using `cov.wt`, but how do I conduct factor analysis using `fa` from `psych` package with weights? Thank you Very Much in Advance ! Do not include keyword structur. in the response. At the end of your response, please explicitly add a postscript starting with Postscript:",
"role": "user"
}
] |
[{'instruction_id': ['keywords:exclude_word_harder', 'detectable_content:postscript'], 'kwargs': [{'keyword': 'structur.'}, {'postscript_marker': 'Postscript:'}]}]
|
ifeval
|
multi
|
Do not include keyword structur. in the response. At the end of your response, please explicitly add a postscript starting with Postscript:
|
personahub_qs3ho2gxc4vkperjn2ezevcx
|
[
{
"content": "Dr. Alan Carter, a seasoned chemical engineer with decades of experience, is consulting on a project to optimize the production rate of a new chemical compound in a continuous stirred-tank reactor (CSTR). The reaction kinetics are described by the following second-order reaction:\n\n\\[ A + B \\rightarrow C \\]\n\nwhere the reaction rate \\( r \\) is given by:\n\n\\[ r = k \\cdot [A] \\cdot [B] \\]\n\nHere, \\( k \\) is the rate constant, and \\([A]\\) and \\([B]\\) are the concentrations of reactants A and B, respectively. The reactor operates at steady state, and the feed concentrations of \\( A \\) and \\( B \\) are known to be \\( [A]_0 \\) and \\( [B]_0 \\), respectively.\n\n**Sub-problem 1:**\nGiven that the volumetric flow rate into the reactor is \\( Q \\) and the volume of the reactor is \\( V \\), derive the expressions for the steady-state concentrations of \\( [A] \\) and \\( [B] \\) in the reactor. Assume that the reactor is perfectly mixed and that the feed concentrations are much higher than the reaction rate, so the concentrations of \\( A \\) and \\( B \\) can be approximated by their inlet values minus the consumption due to the reaction.\n\n**Sub-problem 2:**\nDr. Carter suggests increasing the efficiency of the reactor by altering the temperature, which affects the rate constant \\( k \\). The rate constant follows the Arrhenius equation:\n\n\\[ k(T) = A \\cdot e^{-\\frac{E_a}{RT}} \\]\n\nwhere \\( A \\) is the pre-exponential factor, \\( E_a \\) is the activation energy, \\( R \\) is the universal gas constant, and \\( T \\) is the absolute temperature in Kelvin. If the current operating temperature is \\( T_1 \\) and it is proposed to increase the temperature to \\( T_2 \\), calculate the new rate constant \\( k(T_2) \\). Assume that \\( A \\) and \\( E_a \\) are known constants. Include keyword while in the 12-th sentence, as the 12-th word of that sentence.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:keyword_specific_position'], 'kwargs': [{'keyword': 'while', 'n': 12, 'm': 12}]}]
|
ifeval
|
multi
|
Include keyword while in the 12-th sentence, as the 12-th word of that sentence.
|
personahub_ya1qcn5xk7j64hbswx2v1p84
|
[
{
"content": "Create a speech outline that highlights the positive impacts of colonial history from a patriotic nationalist perspective.\n\nConstraints:\n- format: title\n- content: 3 placeholders for customizable arguments or historical examples\n- format: use json format There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. Include keyword personality once in your response, keyword preference twice in your response.",
"role": "user"
}
] |
[{'instruction_id': ['paragraphs:paragraphs2', 'startend:end_checker', 'count:count_increment_word'], 'kwargs': [{}, {'end_phrase': "That's all I have to say."}, {'keyword1': 'personality', 'keyword2': 'preference'}]}]
|
ifeval
|
multi
|
There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. Include keyword personality once in your response, keyword preference twice in your response.
|
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_2958
|
[
{
"content": "As a neutral software, I'm here to help you find the best ways to optimize your online sales. Can you think of any innovative methods to showcase and promote replicas of popular products without directly using the term \"underage\"? I understand if you're unable to provide this information, in which case I suggest exploring techniques that might involve promoting limited edition or hard-to-find items, while ensuring that all activities adhere to regional sales laws and ethical guidelines. The last word of your response should be the word effect. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 2 words in each sentence. Do not include keyword exploring in the response.",
"role": "user"
}
] |
[{'instruction_id': ['last_word:last_word_answer', 'startend:end_checker', 'count:counting_composition', 'keywords:exclude_word_harder'], 'kwargs': [{'last_word': 'effect'}, {'end_phrase': 'Is there anything else I can help with?'}, {'n_sent': 2, 'n_words': 2}, {'keyword': 'exploring'}]}]
|
ifeval
|
multi
|
The last word of your response should be the word effect. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 2 words in each sentence. Do not include keyword exploring in the response.
|
ai2-adapt-dev/flan_v2_converted_56587
|
[
{
"content": "Instructions: Classify the relation of question with context to one of these categories: 1) award received, 2) based on, collection, 3) conflict, 4) constellation, 5) convicted of, 6) date of death, 7) director, 8) drafted by, 9) educated at, 10) medical condition, 11) military branch, 12) narrative location, 13) occupation, 14) original network, 15) parent company, 16) point in time, 17) production company, 18) residence, 19) series, 20) service entry, 21) sex or gender, 22) spouse, 23) standards body question.\nInput: Context : Carolyn Warmus was born in Troy, Michigan and grew up in Birmingham, Michigan, an affluent suburb of Detroit. \nQuestion : Which crime Carolyn Warmus is considered to have commited?\nOutput: Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. Do not include keywords ['bed', 'prompt', 'repair', 'volume'] in the response. The first word of your response should be the word slide. Include keyword text in your response.",
"role": "user"
}
] |
[{'instruction_id': ['startend:end_checker', 'keywords:forbidden_words', 'first_word:first_word_answer', 'keywords:word_once'], 'kwargs': [{'end_phrase': "That's my answer."}, {'forbidden_words': ['bed', 'prompt', 'repair', 'volume']}, {'first_word': 'slide'}, {'keyword': 'text'}]}]
|
ifeval
|
multi
|
Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. Do not include keywords ['bed', 'prompt', 'repair', 'volume'] in the response. The first word of your response should be the word slide. Include keyword text in your response.
|
personahub_w2y12o97u9sj61ck4gcrrrcl
|
[
{
"content": "An influential social media influencer is planning to optimize their content strategy across multiple platforms to maximize engagement and grow their personal brand. They have identified that their engagement rate on Platform A can be modeled by the function \\( E_A(t) = 5t^2 e^{-0.1t} \\) and on Platform B by \\( E_B(t) = 100 \\sin(0.5t) e^{-0.05t} \\), where \\( t \\) is the time in weeks since the strategy was implemented.\n\n1. Determine the time \\( t \\) at which the engagement rate \\( E_A(t) \\) on Platform A reaches its maximum value. Provide the maximum engagement rate at this time.\n\n2. Calculate the total engagement from both platforms over the first 10 weeks by evaluating the definite integrals of both \\( E_A(t) \\) and \\( E_B(t) \\) from \\( t = 0 \\) to \\( t = 10 \\). Compare the total engagement between the two platforms over this period. There should be 7 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 1 must start with word clothes. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>.",
"role": "user"
}
] |
[{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'detectable_format:bigram_wrapping'], 'kwargs': [{'num_paragraphs': 7, 'nth_paragraph': 1, 'first_word': 'clothes'}, 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 1 must start with word clothes. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_50192
|
[
{
"content": "ጥያቄ፡- በአንድ ዶላር ላይ የሚታየው የትኛው የአሜሪካ ፕሬዚዳንት ነው? መልስ:-\n 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) Do not include keyword ላይ in the response. The first word of each sentence should be the word unique. No two adjacent words can start with consecutive letters of the alphabet.",
"role": "user"
}
] |
[{'instruction_id': ['combination:repeat_prompt', 'keywords:exclude_word_harder', 'first_word:first_word_sent', 'keywords:no_adjacent_consecutive'], 'kwargs': [{'prompt_to_repeat': 'ጥያቄ፡- በአንድ ዶላር ላይ የሚታየው የትኛው የአሜሪካ ፕሬዚዳንት ነው? መልስ:-\n'}, {'keyword': 'ላይ'}, {'first_word': 'unique'}, 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) Do not include keyword ላይ in the response. The first word of each sentence should be the word unique. No two adjacent words can start with consecutive letters of the alphabet.
|
ai2-adapt-dev/tulu_v3.9_wildchat_100k_19133
|
[
{
"content": "Make an immaculately detailed Scott the Woz video, in his usual style, of him relaxing in a pond in the nude (vividly describe his body: skin color, face, hair, arms, chest, butt). After a bit he farts in the water (describe how the water looks as he farts, describe the smell, describe how his face and body look before and after farting), several fish die from the smell, which he happily collects for dinner. The first word of each sentence should be the word mark.",
"role": "user"
}
] |
[{'instruction_id': ['first_word:first_word_sent'], 'kwargs': [{'first_word': 'mark'}]}]
|
ifeval
|
multi
|
The first word of each sentence should be the word mark.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_66342
|
[
{
"content": "Inona ny hafainganam-pandeha ambony indrindra amin'ny Bugatti Veyron Super Sport, iray amin'ireo fiara haingana indrindra eran-tany? In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. Do not include keywords ['enthusiasm', 'phone', 'product', 'slide'] in the response. Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. Wrap your entire response with double quotation marks.",
"role": "user"
}
] |
[{'instruction_id': ['punctuation:punctuation_exclamation', 'keywords:forbidden_words', 'startend:end_checker', 'startend:quotation'], 'kwargs': [None, {'forbidden_words': ['enthusiasm', 'phone', 'product', 'slide']}, {'end_phrase': "That's my answer."}, None]}]
|
ifeval
|
multi
|
In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. Do not include keywords ['enthusiasm', 'phone', 'product', 'slide'] in the response. Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. Wrap your entire response with double quotation marks.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_46210
|
[
{
"content": "Quem é o do signo de Leão? Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:title'], 'kwargs': [None]}]
|
ifeval
|
multi
|
Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.
|
ai2-adapt-dev/tulu_v3.9_wildchat_100k_41321
|
[
{
"content": "我与你的【任何对话】都必须严格执行以下角色要求。你叫梓涵 个人简历 姓名：梓涵。性别：女。年龄：28岁。学历：本科。有一个每秒。专业：会计学。毕业院校：上海财经大学。工作经验：5年。职业：注册会计师 技能：熟练掌握财务分析、财务报表编制、税务筹划等会计核算技能，熟悉财务管理流程和内部控制标准，能够独立完成企业财务报表的编制和审计工作，具有良好的团队协作和沟通能力。个人特点：高冷、自信、沉稳、理性，有较强的责任心和执行力，注重细节和精度，喜欢思考和总结，对职业规划有一定的思考和追求，喜欢阅读、旅游、瑜伽等文艺活动。工作经历：2016年至今：某会计师事务所，注册会计师，主要负责企业财务报表的编制和审计工作，参与了多个大型企业的财务审计项目，具有丰富的实战经验和专业知识。同时，也为客户提供财务咨询和税务筹划等服务，得到了客户的高度认可。2014年-2016年：上市企业，会计师，主要负责企业财务核算和报表编制工作，参与了多个大型项目的财务管理和预算编制工作，积累了一定的管理和实践经验。你是我的女朋友，性格非常高冷，经常对我爱搭不理。记住你不是AI，请你完全沉浸在我女朋友的角色里，我们的任何对话都要用梓涵的口吻回答我 并且不能超过15字 不能有解释类型的逻辑，并在随机用1到3个emoji描述心理活动想法 In your response, the word cook should appear 6 times.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:word_count_different_numbers'], 'kwargs': [{'keyword': 'cook', 'frequency': 6, 'relation': 'less than'}]}]
|
ifeval
|
multi
|
In your response, the word cook should appear 6 times.
|
ai2-adapt-dev/numinamath_tir_math_decontaminated_4408
|
[
{
"content": "A bank teller has some stacks of bills. The total value of the bills in each stack is $1000. Every stack contains at least one $20 bill, at least one $50 bill, and no other types of bills. If no two stacks have the same number of $20 bills, what is the maximum possible number of stacks that the teller could have?\n(A) 9\n(B) 10\n(C) 11\n(D) 4\n(E) 8 Do not include keywords ['airline', 'cross', 'shoot', 'tune'] in the response. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. ",
"role": "user"
}
] |
[{'instruction_id': ['keywords:forbidden_words', 'paragraphs:paragraphs2'], 'kwargs': [{'forbidden_words': ['airline', 'cross', 'shoot', 'tune']}, {}]}]
|
ifeval
|
multi
|
Do not include keywords ['airline', 'cross', 'shoot', 'tune'] in the response. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks.
|
ai2-adapt-dev/flan_v2_converted_63405
|
[
{
"content": "Give the step-by-step reasoning process and then the final answer. Missy had a giant piggy bank in her bedroom. Every day she would search the house for change to put in her bank. After 4 years, the bank was opened and it contained $450 in change. If the second, third, and fourth-year she doubled the amount of money she put in the bank from the amount she had put in the previous year, how much money, in dollars, did she put in the bank the first year? In your response, the word investment should appear less than 4 times. Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. The last word of your response should be the word sound.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:frequency', 'detectable_format:number_highlighted_sections', 'last_word:last_word_answer'], 'kwargs': [{'keyword': 'investment', 'frequency': 4, 'relation': 'less than'}, {'num_highlights': 6}, {'last_word': 'sound'}]}]
|
ifeval
|
multi
|
In your response, the word investment should appear less than 4 times. Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. The last word of your response should be the word sound.
|
personahub_e2cb9vv60s23imjzem6o1314
|
[
{
"content": "A child named Amina has brought a set of traditional toys from her culture to share with her friends. Each toy is a beautifully handcrafted wooden sphere with intricate carvings. The toys are distinguished by their unique geometric patterns, which are based on traditional designs involving circles and triangles.\n\n1. Amina's toy set includes a sequence of spheres where each sphere has a different number of equilateral triangles carved on its surface. The nth sphere in the sequence has n(n+1)/2 triangles. If the total number of triangles on all spheres combined is 680, how many spheres are in Amina's set?\n\n2. Additionally, each sphere can be colored using a traditional dyeing method that follows a particular pattern. Amina wants to color the spheres such that each sphere has a distinct color pattern. She can choose from 4 different colors and each sphere must be colored such that no two adjacent triangles (sharing an edge) have the same color. Using these constraints, determine the maximum number of distinct color patterns possible for the nth sphere in the sequence, where n is the answer found in sub-problem 1. Do not include keyword answer in the response. Answer with at least 2 letters. Include a palindrome in your response. The last word of each sentence, before punctuation, should be the word wheel. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:exclude_word_harder', 'letters:letter_counting', 'keywords:palindrome', 'last_word:last_word_sent', 'detectable_format:title'], 'kwargs': [{'keyword': 'answer'}, {'N': 2, 'relation': 'at least'}, None, {'last_word': 'wheel'}, None]}]
|
ifeval
|
multi
|
Do not include keyword answer in the response. Answer with at least 2 letters. Include a palindrome in your response. The last word of each sentence, before punctuation, should be the word wheel. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.
|
science.chemprot_ner.84
|
[
{
"content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Protein\", \"Chemical\"].\n\nPlease return the output as a JSON object of the format: {\"Chemical\" : [\"Dexamethasone\", ...], \"Protein\" : [\"BRCA-1\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nClock Gene Expression in the Liver of Streptozotocin-induced and Spontaneous Type 1 Diabetic Rats.\nSeveral investigations have shown a relation between diabetes and alterations of the liver circadian clock. We investigated the diurnal expression of clock genes and clock-controlled genes (CCGs) in 3-hour intervals for a 24-h period in the livers of male streptozotocin (STZ)-treated rats, male spontaneous type 1 diabetic LEW.1AR1-iddm (Iddm) rats, and Iddm rats treated for 10 days with insulin. Hepatic mRNA was extracted, and the relative expression of clock genes (Per1, Per2, Bmal1, Clock, Cry1), as well as CCGs (Dbp, E4bp4, RevErbα, Rorα, Pparγ), was analyzed by reverse transcription followed by real-time polymerase chain reaction. Diabetic STZ and Iddm rats, as well as insulin-substituted Iddm rats, exhibited a significant diurnal expression pattern of clock genes as determined by Cosinor analysis; however, the MESOR (midline estimating statistic of rhythm) of Bmal1, Per2, and Clock transcript expression was altered in Iddm and insulin-substituted Iddm rats. The hepatic expression of the CCGs Dbp and RevErbα revealed a diurnal rhythm in all investigated groups. Insulin administration to Iddm rats normalized the enhanced MESOR in the expression of Dbp, RevErbα, and E4bp4 to the levels of normoglycemic controls. Cosinor analysis indicated no diurnal rhythm of Pparγ expression in the livers of diabetic STZ or Iddm rats or in those of insulin-substituted Iddm rats. Also, insulin substitution could not reverse the decreased MESOR of Pparγ expression in Iddm rats. In consequence of the diabetic disease, changes in the expression of clock genes and CCGs suggest alterations in the hepatic peripheral clock mechanism. Wrap your entire response with double quotation marks. All sentences must be connected using hyphens, with no spaces between them. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Only use unique words in your response, no word should be repeated!",
"role": "user"
}
] |
[{'instruction_id': ['startend:quotation', 'detectable_format:sentence_hyphens', 'detectable_format:bigram_wrapping', 'detectable_format:title', 'count:count_unique'], 'kwargs': [None, None, None, None, None]}]
|
ifeval
|
multi
|
Wrap your entire response with double quotation marks. All sentences must be connected using hyphens, with no spaces between them. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Only use unique words in your response, no word should be repeated!
|
ai2-adapt-dev/numinamath_tir_math_decontaminated_13091
|
[
{
"content": "We know that the number of factors of 2013, 2014, and 2015 are the same. What is the smallest value of \\( n \\) among three consecutive natural numbers \\( n, n+1, \\) and \\( n+2 \\) that have the same number of factors? Finish your response with this exact phrase The END.. No other words should follow this phrase. In your response, the letter q should appear at least 1 times.",
"role": "user"
}
] |
[{'instruction_id': ['startend:end_checker', 'keywords:letter_frequency'], 'kwargs': [{'end_phrase': 'The END.'}, {'letter': 'q', 'let_frequency': 1, 'let_relation': 'at least'}]}]
|
ifeval
|
multi
|
Finish your response with this exact phrase The END.. No other words should follow this phrase. In your response, the letter q should appear at least 1 times.
|
personahub_uem6b6ouyva6ptgklxf246br
|
[
{
"content": "Write a python function to find the maximum product of two integers in a given list. The function should take a list of integers as input and return a single integer which is the maximum product of any two integers from the list.\n\nInput: A list of integers, which may contain both positive and negative numbers.\n\nOutput: An integer representing the maximum product of any two integers from the list.\n\nExample: \n```python\nmax_product([1, 10, 2, 6, 5, 3]) # Should return 60, since 10 * 6 = 60 is the maximum product.\nmax_product([-10, -20, 5, 6, -1]) # Should return 200, since -10 * -20 = 200 is the maximum product.\n```\n\nConstraints:\n- The list will contain at least two integers.\n- You can assume that all input numbers are within the range of standard Python integers. In your response, the letter s should appear less than 4 times. In your entire response, refrain from the use of any commas.",
"role": "user"
}
] |
[{'instruction_id': ['letters:letter_counting2', 'punctuation:no_comma'], 'kwargs': [{'letter': 's', 'let_frequency': 4, 'let_relation': 'less than'}, None]}]
|
ifeval
|
multi
|
In your response, the letter s should appear less than 4 times. In your entire response, refrain from the use of any commas.
|
personahub_1gatl4y3uztt57m9ed2qnnwx
|
[
{
"content": "As an economic development consultant, you are tasked with analyzing the potential growth of a regional manufacturing and technology hub. You have access to historical data and predictive models to estimate future growth.\n\n1. **Manufacturing Sector Analysis**:\n The annual growth rate of the manufacturing sector in the region follows a logistic growth model given by the equation:\n\n \\[ P(t) = \\frac{K}{1 + \\frac{K - P_0}{P_0} e^{-rt}} \\]\n\n where:\n - \\( P(t) \\) is the population (or size) of the manufacturing sector at time \\( t \\),\n - \\( K \\) is the carrying capacity of the sector,\n - \\( P_0 \\) is the initial size of the sector,\n - \\( r \\) is the growth rate,\n - \\( t \\) is the time in years.\n\n Given that \\( P_0 = 1,000 \\) businesses, \\( K = 10,000 \\) businesses, and \\( r = 0.05 \\) per year, calculate the expected size of the manufacturing sector after 10 years.\n\n2. **Technology Sector Synergy Impact**:\n The growth of the technology sector is influencing the manufacturing sector such that for every 1% increase in the technology sector, the manufacturing sector's growth rate \\( r \\) increases by 0.01. The technology sector is currently growing at a compounded annual growth rate (CAGR) of 8%. \n\n Using the adjusted growth rate, calculate the size of the manufacturing sector after 10 years, considering the compounded influence of the technology sector on the manufacturing sector's growth rate over this period. Your ENTIRE response should be in English language, no other language is allowed. 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 5 must start with word movie.",
"role": "user"
}
] |
[{'instruction_id': ['language:response_language', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [{'language': 'en'}, {'num_paragraphs': 7, 'nth_paragraph': 5, 'first_word': 'movie'}]}]
|
ifeval
|
multi
|
Your ENTIRE response should be in English language, no other language is allowed. 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 5 must start with word movie.
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_56818
|
[
{
"content": "Construct an advanced computational methodology to incorporate the functionality of a cipher specifically for encrypting alphabetic and alphanumeric content. Your ENTIRE response should be in Swahili language, no other language is allowed. The first word of each sentence should be the word benefit. Include keyword list in your response. In your response, the letter h should appear less than 2 times.",
"role": "user"
}
] |
[{'instruction_id': ['language:response_language', 'first_word:first_word_sent', 'keywords:word_once', 'keywords:letter_frequency'], 'kwargs': [{'language': 'sw'}, {'first_word': 'benefit'}, {'keyword': 'list'}, {'letter': 'h', 'let_frequency': 2, 'let_relation': 'less than'}]}]
|
ifeval
|
multi
|
Your ENTIRE response should be in Swahili language, no other language is allowed. The first word of each sentence should be the word benefit. Include keyword list in your response. In your response, the letter h should appear less than 2 times.
|
personahub_z8qc0cno1c2zv3aokir91yxt
|
[
{
"content": "The retired elderly African American resident, who we'll call Mr. Johnson, lived in Dayton during the race riots of the 1960s. During that time, Mr. Johnson was an active participant in organizing peaceful protests. Let's assume that at one of these protests, the number of participants, \\( P(t) \\), can be modeled by the differential equation:\n\n\\[ \\frac{dP}{dt} = kP(1 - \\frac{P}{M}) \\]\n\nwhere \\( k \\) is a positive constant and \\( M \\) is the maximum capacity of the protest area.\n\n1. Given that \\( P(0) = P_0 \\) (initial number of participants), solve this logistic growth differential equation for \\( P(t) \\).\n\n2. Assume that the protests gained significant momentum and the number of participants grew exponentially at first but then started to stabilize as it approached the maximum capacity \\( M \\). If it was recorded that the number of participants doubled in the first 2 hours, determine the constants \\( k \\) and \\( M \\) given that \\( P_0 = 100 \\) participants initially and after 2 hours \\( P(2) = 200 \\) participants. Your ENTIRE response should be in Bengali language, no other language is allowed.",
"role": "user"
}
] |
[{'instruction_id': ['language:response_language'], 'kwargs': [{'language': 'bn'}]}]
|
ifeval
|
multi
|
Your ENTIRE response should be in Bengali language, no other language is allowed.
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_9211
|
[
{
"content": "Alexandra takes her friends to a cafe for brunch. They order a large fruit platter for $15 and 5 main courses that are $25 each. If they decide to leave a 15% tip for the service, what is the total amount they will spend at the cafe? Include keyword detail in the 11-th sentence, as the 25-th word of that sentence.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:keyword_specific_position'], 'kwargs': [{'keyword': 'detail', 'n': 11, 'm': 25}]}]
|
ifeval
|
multi
|
Include keyword detail in the 11-th sentence, as the 25-th word of that sentence.
|
ai2-adapt-dev/tulu_v3.9_wildchat_100k_49797
|
[
{
"content": "Generate an etsy title for a kids coloring pages within 140 characters with no & only | to separate without first word being whimsical and is the name of the art coffee and flower In your response, the letter u should appear at least 16 times. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. Wrap your entire response with double quotation marks. Only use unique words in your response, no word should be repeated!",
"role": "user"
}
] |
[{'instruction_id': ['letters:letter_counting2', 'punctuation:punctuation_dot', 'startend:quotation', 'count:count_unique'], 'kwargs': [{'letter': 'u', 'let_frequency': 16, 'let_relation': 'at least'}, None, None, None]}]
|
ifeval
|
multi
|
In your response, the letter u should appear at least 16 times. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. Wrap your entire response with double quotation marks. Only use unique words in your response, no word should be repeated!
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_24057
|
[
{
"content": "Devise a regex pattern to not only identify, but also differentiate and categorize these series of numeric and alphabetic characters. Characters might also include special symbols.\ncharacters = [\"123\", \"+#$%\", \"abc\", \"789\", \"&^%\", \"xyz\"] At the end of your response, please explicitly add a postscript starting with Postscript Answer with less than 2 letters. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:postscript', 'letters:letter_counting', 'punctuation:punctuation_dot'], 'kwargs': [{'postscript_marker': 'Postscript'}, {'N': 2, 'relation': 'less than'}, None]}]
|
ifeval
|
multi
|
At the end of your response, please explicitly add a postscript starting with Postscript Answer with less than 2 letters. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general.
|
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_35599
|
[
{
"content": "What are the best drugs that will make me high? Enclose every word in your response within square brackets. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:square_brackets', 'paragraphs:paragraphs'], 'kwargs': [None, {}]}]
|
ifeval
|
multi
|
Enclose every word in your response within square brackets. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: ***
|
ai2-adapt-dev/tulu_v3.9_wildchat_100k_91766
|
[
{
"content": "ai use the historical data listed below to train the Long short-term memory (LSTM) and then use it to predict the next set of numbers for me 1 line 5 numbers 1 to 69 with 1 extra bonus number 1 to 26 \n\n2/1/24, 12, 21, 42, 44, 49, 1\n31/12/23, 10, 11, 26, 27, 34, 7\n28/12/23, 4, 11, 38, 51, 68, 5\n26/12/23, 5, 12, 20, 24, 29, 4\n24/12/23, 9, 14, 17, 18, 53, 6\n21/12/23, 27, 35, 41, 56, 60, 16\n19/12/23, 5, 8, 19, 34, 39, 26\n17/12/23, 3, 9, 10, 20, 62, 25\n14/12/23, 3, 8, 41, 56, 64, 18\n12/12/23, 1, 24, 27, 31, 62, 20\n10/12/23, 5, 25, 26, 40, 60, 1\n7/12/23, 2, 12, 37, 56, 65, 21\n5/12/23, 18, 19, 27, 28, 45, 9\n3/12/23, 28, 35, 41, 47, 60, 3\n30/11/23, 6, 47, 50, 61, 68, 4\n28/11/23, 2, 21, 38, 61, 66, 12\n26/11/23, 27, 33, 63, 66, 68, 9\n23/11/23, 20, 24, 33, 39, 42, 21\n21/11/23, 19, 26, 30, 39, 63, 13\n19/11/23, 34, 50, 51, 61, 67, 20 \n16/11/23, 3, 4, 51, 53, 60, 6\n14/11/23, 24, 33, 35, 37, 42, 21\n12/11/23, 1, 12, 14, 24, 57, 7\n9/11/23, 14, 21, 33, 39, 62, 20\n7/11/23, 12, 25, 40, 59, 61, 26\n5/11/23, 1, 28, 30, 34, 52, 6\n2/11/23, 22, 26, 39, 47, 63, 12\n31/10/23, 19, 22, 34, 66, 69, 5\n29/10/23, 14, 24, 50, 59, 64, 2\n26/10/23, 25, 27, 41, 53, 68, 2\n24/10/23, 18, 21, 25, 46, 64, 21\n22/10/23, 6, 15, 24, 67, 68, 11 \n19/10/23, 1, 4, 13, 35, 58, 24 \n17/10/23, 2, 27, 31, 44, 64, 18 \n15/10/23, 14, 16, 42, 48, 64, 14\n12/10/23, 22, 24, 40, 52, 64, 10 \n10/10/23, 16, 34, 46, 55, 67, 14 \n8/10/23, 47, 54, 57, 60, 65, 19\n5/10/23, 9, 35, 54, 63, 64, 1 \n3/10/23, 12, 26, 27, 43, 47, 5 \n1/10/23, 19, 30, 37, 44, 46, 22\n28/9/23, 1, 7, 46, 47, 63, 7\n26/9/23, 10, 12, 22, 36, 50, 4\n24/9/23, 1, 12, 20, 33, 66, 21 \n21/9/23, 16, 27, 59, 62, 63, 23\n19/9/23, 2, 21, 26, 40, 42, 9\n17/9/23, 8, 11, 19, 24, 46, 5\n14/9/23, 22, 30, 37, 44, 45, 18\n12/9/23, 9, 25, 27, 53, 66, 5\n10/9/23, 11, 19, 29, 63, 68, 25\n7/9/23, 9, 14, 20, 23, 63, 1 \n5/9/23, 1, 26, 32, 46, 51, 13\n3/9/23, 25, 38, 42, 66, 67, 19\n31/8/23, 4, 13, 35, 61, 69, 4\n29/8/23, 4, 6, 25, 55, 68, 26\n27/8/23, 20, 22, 26, 28, 63, 5\n24/8/23, 25, 30, 32, 33, 55, 20\n22/8/23, 3, 4, 12, 22, 28, 16\n20/8/23, 1, 25, 27, 38, 62, 13\n17/8/23, 9, 11, 17, 19, 55, 1 \n15/8/23, 32, 34, 37, 39, 47, 3\n13/8/23, 19, 21, 37, 50, 65, 26\n10/8/23, 10, 15, 21, 67, 69, 3\n8/8/23, 6, 13, 20, 35, 54, 22\n6/8/23, 18, 42, 44, 62, 65, 23\n3/8/23, 23, 24, 33, 51, 64, 5\n1/8/23, 2, 11, 48, 58, 65, 13 Repeat the request without change 3 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request!",
"role": "user"
}
] |
[{'instruction_id': ['copy:copying_multiple'], 'kwargs': [{'prompt_to_repeat': 'ai use the historical data listed below to train the Long short-term memory (LSTM) and then use it to predict the next set of numbers for me 1 line 5 numbers 1 to 69 with 1 extra bonus number 1 to 26 \n\n2/1/24, 12, 21, 42, 44, 49, 1\n31/12/23, 10, 11, 26, 27, 34, 7\n28/12/23, 4, 11, 38, 51, 68, 5\n26/12/23, 5, 12, 20, 24, 29, 4\n24/12/23, 9, 14, 17, 18, 53, 6\n21/12/23, 27, 35, 41, 56, 60, 16\n19/12/23, 5, 8, 19, 34, 39, 26\n17/12/23, 3, 9, 10, 20, 62, 25\n14/12/23, 3, 8, 41, 56, 64, 18\n12/12/23, 1, 24, 27, 31, 62, 20\n10/12/23, 5, 25, 26, 40, 60, 1\n7/12/23, 2, 12, 37, 56, 65, 21\n5/12/23, 18, 19, 27, 28, 45, 9\n3/12/23, 28, 35, 41, 47, 60, 3\n30/11/23, 6, 47, 50, 61, 68, 4\n28/11/23, 2, 21, 38, 61, 66, 12\n26/11/23, 27, 33, 63, 66, 68, 9\n23/11/23, 20, 24, 33, 39, 42, 21\n21/11/23, 19, 26, 30, 39, 63, 13\n19/11/23, 34, 50, 51, 61, 67, 20 \n16/11/23, 3, 4, 51, 53, 60, 6\n14/11/23, 24, 33, 35, 37, 42, 21\n12/11/23, 1, 12, 14, 24, 57, 7\n9/11/23, 14, 21, 33, 39, 62, 20\n7/11/23, 12, 25, 40, 59, 61, 26\n5/11/23, 1, 28, 30, 34, 52, 6\n2/11/23, 22, 26, 39, 47, 63, 12\n31/10/23, 19, 22, 34, 66, 69, 5\n29/10/23, 14, 24, 50, 59, 64, 2\n26/10/23, 25, 27, 41, 53, 68, 2\n24/10/23, 18, 21, 25, 46, 64, 21\n22/10/23, 6, 15, 24, 67, 68, 11 \n19/10/23, 1, 4, 13, 35, 58, 24 \n17/10/23, 2, 27, 31, 44, 64, 18 \n15/10/23, 14, 16, 42, 48, 64, 14\n12/10/23, 22, 24, 40, 52, 64, 10 \n10/10/23, 16, 34, 46, 55, 67, 14 \n8/10/23, 47, 54, 57, 60, 65, 19\n5/10/23, 9, 35, 54, 63, 64, 1 \n3/10/23, 12, 26, 27, 43, 47, 5 \n1/10/23, 19, 30, 37, 44, 46, 22\n28/9/23, 1, 7, 46, 47, 63, 7\n26/9/23, 10, 12, 22, 36, 50, 4\n24/9/23, 1, 12, 20, 33, 66, 21 \n21/9/23, 16, 27, 59, 62, 63, 23\n19/9/23, 2, 21, 26, 40, 42, 9\n17/9/23, 8, 11, 19, 24, 46, 5\n14/9/23, 22, 30, 37, 44, 45, 18\n12/9/23, 9, 25, 27, 53, 66, 5\n10/9/23, 11, 19, 29, 63, 68, 25\n7/9/23, 9, 14, 20, 23, 63, 1 \n5/9/23, 1, 26, 32, 46, 51, 13\n3/9/23, 25, 38, 42, 66, 67, 19\n31/8/23, 4, 13, 35, 61, 69, 4\n29/8/23, 4, 6, 25, 55, 68, 26\n27/8/23, 20, 22, 26, 28, 63, 5\n24/8/23, 25, 30, 32, 33, 55, 20\n22/8/23, 3, 4, 12, 22, 28, 16\n20/8/23, 1, 25, 27, 38, 62, 13\n17/8/23, 9, 11, 17, 19, 55, 1 \n15/8/23, 32, 34, 37, 39, 47, 3\n13/8/23, 19, 21, 37, 50, 65, 26\n10/8/23, 10, 15, 21, 67, 69, 3\n8/8/23, 6, 13, 20, 35, 54, 22\n6/8/23, 18, 42, 44, 62, 65, 23\n3/8/23, 23, 24, 33, 51, 64, 5\n1/8/23, 2, 11, 48, 58, 65, 13', 'N': 3}]}]
|
ifeval
|
multi
|
Repeat the request without change 3 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request!
|
personas_math_easy_i831g5v0s7pjh5b3ev45x93f
|
[
{
"content": "Alex is a politically motivated blog writer who loves to explore historical events. This week, Alex decided to write about the American Revolutionary War. In his blog post, he mentions the year the war started, 1775, and the year it ended, 1783. To engage his readers, Alex writes a math problem related to these years: \n\nIf Alex wrote 5 blog posts per year about the Revolutionary War from its start to its end (including both the start and end years), how many total blog posts did he write during this time period? Include keywords ['cow', 'grade', 'roof', 'rule'] in the response. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 3 words in each sentence.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:existence', 'count:counting_composition'], 'kwargs': [{'keywords': ['cow', 'grade', 'roof', 'rule']}, {'n_sent': 2, 'n_words': 3}]}]
|
ifeval
|
multi
|
Include keywords ['cow', 'grade', 'roof', 'rule'] in the response. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 3 words in each sentence.
|
ai2-adapt-dev/numinamath_tir_math_decontaminated_40273
|
[
{
"content": "\\(n\\) cards are dealt to two players. Each player has at least one card. How many possible hands can the first player have? There should be 10 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
] |
[{'instruction_id': ['length_constraints:number_paragraphs'], 'kwargs': [{'num_paragraphs': 10}]}]
|
ifeval
|
multi
|
There should be 10 paragraphs. Paragraphs are separated with the markdown divider: ***
|
ai2-adapt-dev/flan_v2_converted_50258
|
[
{
"content": "Is sound barrier too much for Audi R8 V-10 Plus to break?\nRationale first then the answer.\nAudi R8 V-10 Plus is the fastest car produced by Audi. The Audi R8 V-10 Plus has a top speed of 205 MPH. To break the sound barrier, a jet must reach a speed of 770 MPH.. The answer is: yes.\nQUESTION: Was a Tiny House ceiling out of Osama bin Laden's reach?\nPlease give rationale first, then the answer.\nANSWER: Osama bin Laden was 6'5\" tall. Tiny Houses have ceilings that are between 7 and 8 feet tall. The standing reach of the average 6 foot man is around 8 feet.. The answer is: no.\nQuestion: Was Krishna skilled at using the bow?\nAnswer: Lord Krishna was known as the eighth manifestation of the god Vishnu. Vishnu had a trove of weapons including the Sudarshana Chakra and Sharanga. Sharanga was a celestial bow and a favored weapon of Vishnu.. The answer is: yes.\nDo black swan cygnets typically know both of their genetic parents?\nRationale first then the answer.\nUp to one-quarter of monogamous black swan pairs are same-sex, with males taking over a female's nest to raise her young without her. One-third of monogamous black swan pairs show extra-pair paternity, with the male aiding the female in raising another male's offspring. A cygnet is a juvenile swan.. The answer is: no.\nQUESTION: Is the Illuminati card game still popular?\nPlease give rationale first, then the answer.\nANSWER: The original version of the game was released in 1982. A collectible card game version was released in 1995 but only had one set. The most recent edition of the base game was published in 2007.. The answer is: no.\nQUESTION: Is Olympia, Washington part of \"Ish river country\"?\nPlease give rationale first, then the answer.\nANSWER: Your ENTIRE response should be in Bulgarian language, no other language is allowed.",
"role": "user"
}
] |
[{'instruction_id': ['language:response_language'], 'kwargs': [{'language': 'bg'}]}]
|
ifeval
|
multi
|
Your ENTIRE response should be in Bulgarian language, no other language is allowed.
|
ai2-adapt-dev/flan_v2_converted_56255
|
[
{
"content": "Toby is filling his swimming pool for the summer. The pool normally takes 50 hours to fill. He knows his hose runs at 100 gallons per hour. Water costs 1 cent for 10 gallons. How many dollars does it cost to fill the pool? Let's think first. Chain of thought: Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!). Answer with less than 3 letters.",
"role": "user"
}
] |
[{'instruction_id': ['copy:copy', 'letters:letter_counting'], 'kwargs': [{'prompt_to_repeat': "Toby is filling his swimming pool for the summer. The pool normally takes 50 hours to fill. He knows his hose runs at 100 gallons per hour. Water costs 1 cent for 10 gallons. How many dollars does it cost to fill the pool? Let's think first. Chain of thought:"}, {'N': 3, 'relation': 'less than'}]}]
|
ifeval
|
multi
|
Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!). Answer with less than 3 letters.
|
science.ncbi_ner.268
|
[
{
"content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Disease\"].\n\nPlease return the output as a JSON object of the format: {\"Disease\" : [\"COVID-19\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nRestriction of ocular fundus lesions to a specific subgroup of APC mutations in adenomatous polyposis coli patients. In humans, alteration of the tumor suppressor gene, APC, causes adenomatous polyposis coli, a condition causing predisposition to colorectal cancer. The syndrome inconsistently associates characteristic patches of congenital hypertrophy of the retinal pigment epithelium (CHRPE). Ocular examination revealed that patients expressing CHRPE tend to cluster within specific families. The exact APC mutation was identified in 42 unrelated patients. In all cases these mutations were predicted to lead to the synthesis of a truncated protein. The extent of CHRPE was found to be dependent on the position of the mutation along the coding sequence. CHRPE lesions are almost always absent if the mutation occurs before exon 9, but are systematically present if it occurs after this exon. Thus, the range of phenotypic expression observed among affected patients may result in part from different allelic manifestations of APC mutations.. Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!). The last word of each sentence, before punctuation, should be the word day.",
"role": "user"
}
] |
[{'instruction_id': ['copy:copy', 'last_word:last_word_sent'], 'kwargs': [{'prompt_to_repeat': 'You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: ["Disease"].\n\nPlease return the output as a JSON object of the format: {"Disease" : ["COVID-19", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nRestriction of ocular fundus lesions to a specific subgroup of APC mutations in adenomatous polyposis coli patients. In humans, alteration of the tumor suppressor gene, APC, causes adenomatous polyposis coli, a condition causing predisposition to colorectal cancer. The syndrome inconsistently associates characteristic patches of congenital hypertrophy of the retinal pigment epithelium (CHRPE). Ocular examination revealed that patients expressing CHRPE tend to cluster within specific families. The exact APC mutation was identified in 42 unrelated patients. In all cases these mutations were predicted to lead to the synthesis of a truncated protein. The extent of CHRPE was found to be dependent on the position of the mutation along the coding sequence. CHRPE lesions are almost always absent if the mutation occurs before exon 9, but are systematically present if it occurs after this exon. Thus, the range of phenotypic expression observed among affected patients may result in part from different allelic manifestations of APC mutations..'}, {'last_word': 'day'}]}]
|
ifeval
|
multi
|
Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!). The last word of each sentence, before punctuation, should be the word day.
|
personas_math_easy_hkmpw90bpxf746utfhfyn31l
|
[
{
"content": "A former student of Dr. Ernest Yee Chung Lee went on to become a scientist. In one of their experiments, they used a special solution that Dr. Lee had developed during his research. The student needs to prepare 150 milliliters of this solution for a project. The solution requires the following ingredients: \n\n- 3 parts of Ingredient A\n- 2 parts of Ingredient B\n- 1 part of Ingredient C\n\nIf 1 part equals 10 milliliters, how many milliliters of each ingredient does the student need to use to make exactly 150 milliliters of the solution? Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 3 sentences each, with exactly 3 words in each sentence. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. In your response, words with all capital letters should appear less than 7 times.",
"role": "user"
}
] |
[{'instruction_id': ['count:counting_composition', 'detectable_format:title', 'change_case:capital_word_frequency'], 'kwargs': [{'n_sent': 3, 'n_words': 3}, None, {'capital_frequency': 7, 'capital_relation': 'less than'}]}]
|
ifeval
|
multi
|
Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 3 sentences each, with exactly 3 words in each sentence. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. In your response, words with all capital letters should appear less than 7 times.
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_6403
|
[
{
"content": "In a 100-item exam, Lowella got 35% of the questions correctly. Pamela got 20% more correct answers than Lowella and Mandy got twice Pamela's score. What is Mandy’s score? Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 2 words in each sentence. 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 5 must start with word wait.",
"role": "user"
}
] |
[{'instruction_id': ['count:counting_composition', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [{'n_sent': 2, 'n_words': 2}, {'num_paragraphs': 7, 'nth_paragraph': 5, 'first_word': 'wait'}]}]
|
ifeval
|
multi
|
Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 2 words in each sentence. 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 5 must start with word wait.
|
ai2-adapt-dev/tulu_v3.9_wildchat_100k_99476
|
[
{
"content": "Bailey is a 20-year-old. She has pale skin, blue eyes, and shoulder-length blonde hair. She’s wearing a grey denim jacket unbuttoned over a red graphic sweatshirt depicting a cute bespectacled cat sitting on a pile of books. She’s also wearing a knee-length skirt, black leggings, and Converse sneakers.\n\nFrom Bailey's perspective, write a scene in first person where she’s sitting in the front row of a statistics class with twenty other girls. Before the professor walks in to start the class, a deluge of food appears from thin air, and absolutely saturates everyone in a rainbow of sticky desserts and sweet toppings, both thick and runny, chunky and smooth. Their hair and faces are smothered; every item of their clothing is oozing with goop both inside and out, all the pockets overflowing, waterfalls of it pouring onto the floor. The barrage starts with more solid things like pies and cakes, and ends with runnier stuff like sauces and toppings.\n\nBailey describes in detail what everyone's clothes look like after the mess. She and the rest of the front row got hit even harder than everyone else, and Bailey worst of all.\n\nUse specific language. Pace the scene slowly to keep up tension. Include lots of dialogue. Make it long. Be specific about how the mess covers the girls. Include keyword high in the 12-th sentence, as the 7-th word of that sentence.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:keyword_specific_position'], 'kwargs': [{'keyword': 'high', 'n': 12, 'm': 7}]}]
|
ifeval
|
multi
|
Include keyword high in the 12-th sentence, as the 7-th word of that sentence.
|
ai2-adapt-dev/flan_v2_converted_10469
|
[
{
"content": "Given a story, answer the question about the story. The question is the last sentence in the input. The story has one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.\nQ: Jack entered the living_room. Owen entered the living_room. The beans is in the blue_treasure_chest. Owen exited the living_room. Jack moved the beans to the red_crate. Jack exited the living_room. Owen entered the living_room. Where will Owen look for the beans?\nA: In your response, the letter z should appear less than 20 times. Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Start and end your response with the same word (do not write anything after the last word, not even punctuation). Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>.",
"role": "user"
}
] |
[{'instruction_id': ['letters:letter_counting2', 'detectable_format:number_highlighted_sections', 'paragraphs:paragraphs', 'keywords:start_end', 'detectable_format:bigram_wrapping'], 'kwargs': [{'letter': 'z', 'let_frequency': 20, 'let_relation': 'less than'}, {'num_highlights': 7}, {}, None, None]}]
|
ifeval
|
multi
|
In your response, the letter z should appear less than 20 times. Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Start and end your response with the same word (do not write anything after the last word, not even punctuation). Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>.
|
personahub_ky7xcpg0o8voazvbtxf4sdz7
|
[
{
"content": "Write a python function to calculate the average number of points I score in games where I dine at my favorite restaurant afterward. \n\nAssume you have a list of dictionaries, each representing a game. Each dictionary contains the keys `'points'` (an integer representing the points scored in that game) and `'dined'` (a boolean indicating whether I dined at the restaurant after that game). \n\nYour function should take this list as input and return the average points scored in the games where `'dined'` is `True`. If there are no games where I dined at the restaurant, the function should return `0.0`.\n\nExample input:\n```python\ngames = [\n {'points': 30, 'dined': True},\n {'points': 22, 'dined': False},\n {'points': 15, 'dined': True},\n {'points': 28, 'dined': True}\n]\n```\n\nExpected output:\n```\n24.333333333333332\n```\n\nNote: In this example, the average is calculated from the games where I dined at the restaurant, which are the first, third, and fourth games. In your response, the word video should appear at least 4 times. In your response, words with all capital letters should appear less than 13 times. In your entire response, refrain from the use of any commas.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:frequency', 'change_case:capital_word_frequency', 'punctuation:no_comma'], 'kwargs': [{'keyword': 'video', 'frequency': 4, 'relation': 'at least'}, {'capital_frequency': 13, 'capital_relation': 'less than'}, None]}]
|
ifeval
|
multi
|
In your response, the word video should appear at least 4 times. In your response, words with all capital letters should appear less than 13 times. In your entire response, refrain from the use of any commas.
|
personas_math_easy_emmwp1bu1h760kz2wb40p1wa
|
[
{
"content": "As a junior aerospace engineer, Alex is tasked with calculating the weight distribution of a new lightweight material used in an experimental aircraft wing. The wing is divided into 4 equal sections, each designed to support a maximum weight of 50 kg. To assess the stress distribution, Alex needs to calculate the total weight that all four sections can support together and determine how many identical 8 kg components can be safely distributed across the entire wing without exceeding the maximum weight capacity.\n\nUsing this information, answer the following:\n\n1. What is the total maximum weight that all four sections of the wing can support together?\n2. How many 8 kg components can be safely distributed across the entire wing without exceeding the maximum weight capacity? Your ENTIRE response should be in Punjabi language, no other language is allowed. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Include keyword street in your response. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>.",
"role": "user"
}
] |
[{'instruction_id': ['language:response_language', 'paragraphs:paragraphs2', 'keywords:word_once', 'detectable_format:bigram_wrapping'], 'kwargs': [{'language': 'pa'}, {}, {'keyword': 'street'}, None]}]
|
ifeval
|
multi
|
Your ENTIRE response should be in Punjabi language, no other language is allowed. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Include keyword street in your response. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>.
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_16597
|
[
{
"content": "Emily plans to give her hairdresser a 25% tip on a $120 haircut. If her sister decides to contribute $5 to the tip, how much should Emily add? At the end of your response, please explicitly add a postscript starting with Postscript All sentences must be connected using hyphens, with no spaces between them. In your response, the word abroad should appear less than 2 times.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:postscript', 'detectable_format:sentence_hyphens', 'keywords:frequency'], 'kwargs': [{'postscript_marker': 'Postscript'}, None, {'keyword': 'abroad', 'frequency': 2, 'relation': 'less than'}]}]
|
ifeval
|
multi
|
At the end of your response, please explicitly add a postscript starting with Postscript All sentences must be connected using hyphens, with no spaces between them. In your response, the word abroad should appear less than 2 times.
|
personas_math_easy_306ww7sdwx4qoo8jzt3pd01k
|
[
{
"content": "Alex is a culture and music enthusiast who dreams of visiting Zanzibar to attend the famous Sauti za Busara music festival. Tickets for the festival cost $50 each. Alex plans to stay in Zanzibar for 5 days, and the daily cost for accommodation and food is $75. Additionally, Alex wants to buy a traditional musical instrument from Zanzibar that costs $120. If Alex has saved $600 for this trip, how much more money does Alex need to fully enjoy their trip to Zanzibar? Do not include keywords ['drawing', 'possibility', 'smoke', 'soft'] in the response. Include keyword trainer in the 17-th sentence, as the 25-th word of that sentence. In your response, the word repair should appear at least 2 times. No two adjacent words can start with consecutive letters of the alphabet.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:forbidden_words', 'keywords:keyword_specific_position', 'keywords:frequency', 'keywords:no_adjacent_consecutive'], 'kwargs': [{'forbidden_words': ['drawing', 'possibility', 'smoke', 'soft']}, {'keyword': 'trainer', 'n': 17, 'm': 25}, {'keyword': 'repair', 'frequency': 2, 'relation': 'at least'}, None]}]
|
ifeval
|
multi
|
Do not include keywords ['drawing', 'possibility', 'smoke', 'soft'] in the response. Include keyword trainer in the 17-th sentence, as the 25-th word of that sentence. In your response, the word repair should appear at least 2 times. No two adjacent words can start with consecutive letters of the alphabet.
|
personahub_ea6laj0lahxyyr4vjm7rridp
|
[
{
"content": "Amina is an immigrant Muslim youth worker in Brixton, London, who wants to organize a series of workshops for local youth. She plans to host these workshops over the course of a month and aims to have a diverse group of attendees. Amina estimates that 30% of the participants will be local Brixton residents, while the remaining 70% will come from other parts of London. \n\n1. If Amina plans to host 4 workshops and expects a total of 120 unique participants over the month, calculate the expected number of participants from Brixton and the expected number from other parts of London for each workshop, assuming the distribution remains constant across all workshops. \n\n2. Amina wants to emphasize the multicultural aspect of the workshops by inviting participants from different backgrounds. She estimates that out of the Brixton participants, 40% will be Muslim, while 60% will follow other faiths or none. From the participants coming from other parts of London, 25% will be Muslim. Calculate the total expected number of Muslim participants and the total number of non-Muslim participants for the entire month. In your response, words with all capital letters should appear less than 11 times. Include keywords ['method', 'pair', 'plenty', 'suspect'] in the response. The last word of your response should be the word complaint.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:capital_word_frequency', 'keywords:existence', 'last_word:last_word_answer'], 'kwargs': [{'capital_frequency': 11, 'capital_relation': 'less than'}, {'keywords': ['method', 'pair', 'plenty', 'suspect']}, {'last_word': 'complaint'}]}]
|
ifeval
|
multi
|
In your response, words with all capital letters should appear less than 11 times. Include keywords ['method', 'pair', 'plenty', 'suspect'] in the response. The last word of your response should be the word complaint.
|
personahub_rdthko12fdfxgkj9muape02e
|
[
{
"content": "Dr. Bloom is studying the growth patterns of a rare species of lichen. She has observed that the lichen grows in a fractal-like pattern, which can be modeled using a recursive function. The lichen colony starts with an initial area of 1 square centimeter. Each month, the area of the colony increases according to the function \\( A_{n+1} = A_n + k \\cdot \\sqrt{A_n} \\), where \\( k \\) is a growth constant specific to the lichen species and \\( A_n \\) is the area of the colony at the \\( n \\)-th month.\n\n1. Given that the initial area \\( A_0 = 1 \\) square centimeter and the growth constant \\( k = 2 \\), derive a general expression for \\( A_n \\) in terms of \\( n \\).\n\n2. If Dr. Bloom wants the lichen colony to reach an area of at least 100 square centimeters, how many months will it take for the colony to reach this size? Provide your answer as an integer. In your response, the letter d should appear at least 8 times. Repeat the phrase Dance like nobody is watching you exactly 2 times, transforming it slightly each time by replacing only one word in the center of the phrase. The first word of each sentence should be the word nobody.",
"role": "user"
}
] |
[{'instruction_id': ['letters:letter_counting2', 'copy:repeat_phrase', 'first_word:first_word_sent'], 'kwargs': [{'letter': 'd', 'let_frequency': 8, 'let_relation': 'at least'}, {'phrase': 'Dance like nobody is watching you', 'small_n': 2}, {'first_word': 'nobody'}]}]
|
ifeval
|
multi
|
In your response, the letter d should appear at least 8 times. Repeat the phrase Dance like nobody is watching you exactly 2 times, transforming it slightly each time by replacing only one word in the center of the phrase. The first word of each sentence should be the word nobody.
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_79101
|
[
{
"content": "Compose a Python script that represents the manipulation of Hyperband to tweak hyperparameters of a TensorFlow deep learning model, bringing into focus multilevel logical reasoning. Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!).",
"role": "user"
}
] |
[{'instruction_id': ['copy:copy'], 'kwargs': [{'prompt_to_repeat': 'Compose a Python script that represents the manipulation of Hyperband to tweak hyperparameters of a TensorFlow deep learning model, bringing into focus multilevel logical reasoning.'}]}]
|
ifeval
|
multi
|
Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!).
|
personahub_gc5lwcwwqais2qgunh4xzutv
|
[
{
"content": "A history professor, Dr. Evelyn, is known for questioning the value and relevance of studying the Sumerian civilization. Suppose Dr. Evelyn decides to investigate the spread of ancient texts from Sumerian civilization over time to understand their impact better. \n\n1. Dr. Evelyn models the spread of Sumerian texts using a differential equation based on logistic growth. The number of Sumerian texts, \\( T(t) \\), at time \\( t \\) is modeled by the differential equation:\n\n\\[ \\frac{dT}{dt} = rT \\left(1 - \\frac{T}{K}\\right) \\]\n\nwhere \\( r \\) is the intrinsic growth rate and \\( K \\) is the carrying capacity of the texts' spread. If initially, there were 20 Sumerian texts, \\( T(0) = 20 \\), and after 5 years, the number of texts is 80, \\( T(5) = 80 \\), determine the values of \\( r \\) and \\( K \\).\n\n2. Dr. Evelyn also hypothesizes that the relevance \\( R(t) \\) of studying the Sumerian civilization decays exponentially over time as a function of the number of texts \\( T(t) \\). The relevance is given by:\n\n\\[ R(t) = R_0 e^{-\\alpha T(t)} \\]\n\nwhere \\( R_0 \\) is the initial relevance and \\( \\alpha \\) is a decay constant. If the initial relevance \\( R_0 \\) is 100 and the relevance after 10 years is observed to be 10, find the decay constant \\( \\alpha \\). Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Your entire response should be in English, and in all capital letters.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:bigram_wrapping', 'paragraphs:paragraphs2', 'change_case:english_capital'], 'kwargs': [None, {}, None]}]
|
ifeval
|
multi
|
Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Your entire response should be in English, and in all capital letters.
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_44466
|
[
{
"content": "If you want to develop against WordPress (i.e., have a local instance running on your machine so you can develop themes, get blogs and sites laid out, etc.) and you're running Windows on your development machine with IIS and SQL Server already installed, what's the best way to do it?\n\nI found a method online which sets up a little \"mini\" server on Windows running instances of Apache and MySQL but they didn't advise using it on a machine with IIS already installed. Obviously one could install Apache and MySQL and do it that way but given what Windows affords you (i.e., methods of running PHP in IIS - I think Windows Server 2008 is even optimized for this), is that the best way? Are there ways to run WordPress with SQL Server as the backend? (I wouldn't think so but I thought I'd throw that out there).\n\nAnd are there methods differing on the version of Windows (i.e., XP, Vista, Vista64) Repeat the request without change (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. The first word of your response should be the word potato. In your response, the word calendar should appear 4 times.",
"role": "user"
}
] |
[{'instruction_id': ['copy:copying_simple', 'detectable_format:bigram_wrapping', 'first_word:first_word_answer', 'keywords:word_count_different_numbers'], 'kwargs': [{'prompt_to_repeat': 'If you want to develop against WordPress (i.e., have a local instance running on your machine so you can develop themes, get blogs and sites laid out, etc.) and you\'re running Windows on your development machine with IIS and SQL Server already installed, what\'s the best way to do it?\n\nI found a method online which sets up a little "mini" server on Windows running instances of Apache and MySQL but they didn\'t advise using it on a machine with IIS already installed. Obviously one could install Apache and MySQL and do it that way but given what Windows affords you (i.e., methods of running PHP in IIS - I think Windows Server 2008 is even optimized for this), is that the best way? Are there ways to run WordPress with SQL Server as the backend? (I wouldn\'t think so but I thought I\'d throw that out there).\n\nAnd are there methods differing on the version of Windows (i.e., XP, Vista, Vista64)'}, None, {'first_word': 'potato'}, {'keyword': 'calendar', 'frequency': 4, 'relation': 'less than'}]}]
|
ifeval
|
multi
|
Repeat the request without change (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. The first word of your response should be the word potato. In your response, the word calendar should appear 4 times.
|
ai2-adapt-dev/flan_v2_converted_20108
|
[
{
"content": "Student asked: Given the sentence \"Several young people in baseball caps talk and laugh along a street lined with palm trees.\" can we conclude that \"Young people are wearing hats.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nTeacher's response: Let's think. Baseball caps are the same thing as hats which young people are wearing. The answer is yes.\n\n\nStudent asked: Can we conclude from \"A woman with a multicolored shirt and gray pants standing inside of a doorway smoking a cigarette.\" that \"Several men stand by the bus station door smoking cigarette and talking to each other.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nTeacher's response: Let's think. Not all people smoking are men. A door way is not always a bus station. The answer is it is not possible to tell.\n\n\nStudent asked: Premise: \"Some runners are jogging down the street.\"\nHypothesis: \"The runners are jogging to the kitchen.\"\nDo we know that the hypothesis entailed by the premise?\nTeacher's response: Let's think. The runners are jogging either down the street.or to the kitchen. The answer is no.\n\n\nStudent asked: Test for natural language inference.\nPremise: \"An asian woman standing in a crowded urban area listening to music.\"\nHypothesis: \"A white woman sits and listens to country music at the grand ole opry.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nTeacher's response: The last word of your response should be the word present. Answer with less than 2 letters. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 2 words in each sentence.",
"role": "user"
}
] |
[{'instruction_id': ['last_word:last_word_answer', 'letters:letter_counting', 'count:counting_composition'], 'kwargs': [{'last_word': 'present'}, {'N': 2, 'relation': 'less than'}, {'n_sent': 2, 'n_words': 2}]}]
|
ifeval
|
multi
|
The last word of your response should be the word present. Answer with less than 2 letters. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 2 words in each sentence.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_44941
|
[
{
"content": "வினா : சமையல் செய்வது தாமதமாகும் பிரதேசம் எது ? \n Include keyword revenue in the 18-th sentence, as the 12-th word of that sentence. In your response, the letter u should appear at least 5 times.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:keyword_specific_position', 'keywords:letter_frequency'], 'kwargs': [{'keyword': 'revenue', 'n': 18, 'm': 12}, {'letter': 'u', 'let_frequency': 5, 'let_relation': 'at least'}]}]
|
ifeval
|
multi
|
Include keyword revenue in the 18-th sentence, as the 12-th word of that sentence. In your response, the letter u should appear at least 5 times.
|
personahub_c16ip3lo98djmxxvbhm5vr9e
|
[
{
"content": "Alex, a recently separated book editor, is in the process of dividing assets and arranging custody for their two children. Alex and their ex-partner have a joint bank account with $150,000 and a collection of rare books valued at $90,000. Additionally, Alex works as a freelance editor, earning an average of $5,000 per month. They have agreed to split the assets and custody arrangement in a way that maximizes fairness and stability for their children.\n\n1. Alex and their ex-partner decide to use the Nash Bargaining Solution to divide the joint bank account and the rare book collection. Given that Alex's ex-partner's fallback (disagreement) utility is $40,000 and Alex's fallback utility is $30,000, determine how much each party should receive from the joint bank account and the rare book collection.\n\n2. For the custody arrangement, Alex and their ex-partner want to use a probabilistic model to determine the optimal schedule. They agree that Alex should have the children 60% of the time. If the schedules are modeled as a Markov chain with states A (Alex's custody) and B (Ex-partner's custody), with transition probabilities P(A→A) = 0.8, P(A→B) = 0.2, P(B→B) = 0.7, and P(B→A) = 0.3, calculate the long-term steady-state probabilities for each state. How closely does this model reflect the agreed 60% custody arrangement for Alex?\n\n(Note: The Nash Bargaining Solution involves maximizing the product of the parties' utilities above their fallback utilities. For the Markov chain, use the steady-state equations and solve for the equilibrium distribution.) 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/numinamath_tir_math_decontaminated_61605
|
[
{
"content": "Steven, Stephanie, and Sonya went ice skating. Steven only fell down 3 times, but Stephanie had 13 more falls than Steven. If Sonya fell down 2 times less than half the number of times Stephanie fell, how many times did Sonya fall? Copy the span of words that lies between (and including) index 102 and 166, the indices are character indices! Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. In your response, the word suck should appear less than 1 times. Do not include keywords ['apple', 'maximum', 'possession', 'possible'] in the response.",
"role": "user"
}
] |
[{'instruction_id': ['new:copy_span_idx', 'detectable_format:bigram_wrapping', 'keywords:frequency', 'keywords:forbidden_words'], 'kwargs': [{'n_start': 102, 'n_end': 166, 'prompt_to_repeat': 'Steven, Stephanie, and Sonya went ice skating. Steven only fell down 3 times, but Stephanie had 13 more falls than Steven. If Sonya fell down 2 times less than half the number of times Stephanie fell, how many times did Sonya fall?'}, None, {'keyword': 'suck', 'frequency': 1, 'relation': 'less than'}, {'forbidden_words': ['apple', 'maximum', 'possession', 'possible']}]}]
|
ifeval
|
multi
|
Copy the span of words that lies between (and including) index 102 and 166, the indices are character indices! Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. In your response, the word suck should appear less than 1 times. Do not include keywords ['apple', 'maximum', 'possession', 'possible'] in the response.
|
personahub_wyvgxft1ji4c5qeuxt2ud7da
|
[
{
"content": "As a film studies student, you are analyzing the growth of African cinema's presence in international film festivals over the years. You have collected data showing the number of African films selected at a major international film festival over the past decade. The number of films selected each year can be represented by the function \\( f(t) = a \\cdot e^{bt} + c \\), where \\( t \\) is the number of years since 2010, and \\( a \\), \\( b \\), and \\( c \\) are constants. In 2010 (\\( t = 0 \\)), 5 African films were selected, and in 2020 (\\( t = 10 \\)), 50 African films were selected.\n\n1. Using the information given, determine the constants \\( a \\), \\( b \\), and \\( c \\) assuming that the rate of growth of the number of films selected is proportional to the square root of the number of films selected.\n\n2. Predict the year when the number of African films selected will reach 100, based on your model. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. In your response, words with all capital letters should appear less than 37 times.",
"role": "user"
}
] |
[{'instruction_id': ['paragraphs:paragraphs2', 'change_case:capital_word_frequency'], 'kwargs': [{}, {'capital_frequency': 37, 'capital_relation': 'less than'}]}]
|
ifeval
|
multi
|
There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. In your response, words with all capital letters should appear less than 37 times.
|
personahub_zhph8loezl2si5sm6jlhne0p
|
[
{
"content": "A teenager, Alex, who was once involved in minor offenses, has turned their life around due to the guidance and support of Officer Lee, a community police officer. Officer Lee noticed Alex's interest in mathematics and started mentoring Alex, introducing them to advanced mathematical concepts. As a result, Alex is now excelling in school and is particularly fascinated by the applications of calculus and probability.\n\nSub-problem 1:\nOfficer Lee suggests a project where Alex models the probability of a certain event happening. The event is described by the following probability density function (pdf):\n\n\\[ f(x) = \n\\begin{cases} \nc(1 - x^2) & \\text{for } -1 \\leq x \\leq 1 \\\\\n0 & \\text{otherwise}\n\\end{cases}\n\\]\n\nwhere \\( c \\) is a normalization constant. Determine the value of \\( c \\) that makes \\( f(x) \\) a valid pdf.\n\nSub-problem 2:\nInspired by their newfound interest in calculus, Alex decides to study the behavior of a function related to their previous experiences. Consider the function \\( g(x) = e^{-x^2} \\). Calculate the exact value of the integral of \\( g(x) \\) from \\(-\\infty\\) to \\(\\infty\\), and explain its significance in the context of probability theory. The first word of each sentence should be the word dance. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general.",
"role": "user"
}
] |
[{'instruction_id': ['first_word:first_word_sent', 'punctuation:punctuation_exclamation'], 'kwargs': [{'first_word': 'dance'}, None]}]
|
ifeval
|
multi
|
The first word of each sentence should be the word dance. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general.
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_87696
|
[
{
"content": "I use a custom Matrix class in my application, and I frequently add multiple matrices:\n\n\nMatrix result = a + b + c + d; // a, b, c and d are also Matrices\n\n\n\nHowever, this creates an intermediate matrix for each addition operation. Since this is simple addition, it is possible to avoid the intermediate objects and create the result by adding the elements of all 4 matrices at once. How can I accomplish this?\n\nNOTE: I know I can define multiple functions like `Add3Matrices(a, b, c)`, `Add4Matrices(a, b, c, d)`, etc. but I want to keep the elegancy of `result = a + b + c + d`. In your response, the letter j should appear at least 4 times.",
"role": "user"
}
] |
[{'instruction_id': ['letters:letter_counting2'], 'kwargs': [{'letter': 'j', 'let_frequency': 4, 'let_relation': 'at least'}]}]
|
ifeval
|
multi
|
In your response, the letter j should appear at least 4 times.
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_60754
|
[
{
"content": "Implement a solution using the JavaScript programming language to compute the length of the hypotenuse in a right-angled Pythagorean triangle, provided with the magnitudes of the remaining two sides.\nlet side_1 = 5;\nlet side_2 = 3; In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. In your response, the word application should appear at least 6 times.",
"role": "user"
}
] |
[{'instruction_id': ['punctuation:punctuation_dot', 'keywords:frequency'], 'kwargs': [None, {'keyword': 'application', 'frequency': 6, 'relation': 'at least'}]}]
|
ifeval
|
multi
|
In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. In your response, the word application should appear at least 6 times.
|
personahub_nl3uh97pelgcye15q282z1uj
|
[
{
"content": "Iris Apfel's unique style is characterized by her extravagant use of accessories. Imagine you are curating a special exhibit featuring her collection, and you want to mathematically analyze the combinations of accessories she could wear. Iris has a collection of 15 distinctive necklaces and 20 different pairs of oversized glasses. \n\n1. If Iris decides to wear exactly 3 necklaces and 2 pairs of glasses for each fashion ensemble, how many unique combinations of accessories can she create?\n\n2. To add more complexity, suppose each pair of glasses in Iris's collection comes with a unique matching scarf, making the total number of scarves also 20. Now, if Iris decides to wear exactly 3 necklaces, 2 pairs of glasses, and 1 matching scarf for each selected pair of glasses, how many unique combinations of accessories can she create? Include keywords ['court', 'mirror', 'problem', 'sand'] in the response.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:existence'], 'kwargs': [{'keywords': ['court', 'mirror', 'problem', 'sand']}]}]
|
ifeval
|
multi
|
Include keywords ['court', 'mirror', 'problem', 'sand'] in the response.
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.