key
stringlengths 7
86
| messages
listlengths 1
1
| ground_truth
stringlengths 62
280k
| dataset
stringclasses 1
value | constraint_type
stringclasses 1
value | constraint
stringlengths 31
956
|
|---|---|---|---|---|---|
personahub_29vmq90421ec9xixvca9tn43 | [
{
"content": "Dr. Elena Martinez is a postdoctoral fellow specializing in economic policy responses to climate change. She is developing a dynamic model to analyze the impact of carbon pricing on greenhouse gas emissions and economic growth. The model is based on a differential equation system that incorporates both economic and environmental variables.\n\n1. Consider the following system of differential equations, where \\( E(t) \\) denotes the level of emissions at time \\( t \\), and \\( G(t) \\) represents the economic growth rate:\n\n\\[\n\\begin{cases}\n\\frac{dE(t)}{dt} = -\\alpha E(t) + \\beta G(t) \\\\\n\\frac{dG(t)}{dt} = \\gamma G(t) - \\delta E(t)\n\\end{cases}\n\\]\n\nHere, \\( \\alpha, \\beta, \\gamma, \\) and \\( \\delta \\) are positive constants. Analyze the stability of the equilibrium points of this system. Determine whether the equilibrium is stable, unstable, or a saddle point.\n\n2. Assuming a carbon pricing policy is introduced such that the price \\( P(t) \\) at time \\( t \\) is given by \\( P(t) = P_0 e^{-\\lambda t} \\), where \\( P_0 \\) is the initial carbon price and \\( \\lambda \\) is a positive constant. Extend the above system to include the effect of \\( P(t) \\) on emissions by modifying the first equation to incorporate a term \\( -\\eta P(t) \\). The modified system is:\n\n\\[\n\\begin{cases}\n\\frac{dE(t)}{dt} = -\\alpha E(t) + \\beta G(t) - \\eta P(t) \\\\\n\\frac{dG(t)}{dt} = \\gamma G(t) - \\delta E(t)\n\\end{cases}\n\\]\n\nAnalyze how the introduction of carbon pricing affects the long-term behavior of emissions \\( E(t) \\). What conditions on the parameters \\(\\alpha, \\beta, \\gamma, \\delta, \\eta, P_0, \\text{and } \\lambda \\) will ensure that emissions \\( E(t) \\) asymptotically approach zero? Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Finish your response with this exact phrase The END.. No other words should follow this phrase. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:json_format', 'startend:end_checker', 'change_case:english_lowercase'], 'kwargs': [None, {'end_phrase': 'The END.'}, None]}] | ifeval | multi | Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Finish your response with this exact phrase The END.. No other words should follow this phrase. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_2040 | [
{
"content": "i have a wcf service that does an operation. and in this operation there could be a fault. i have stated that there could be a fault in my service contract. \n\nhere is the code below;\n\n\npublic void Foo()\n{\n try\n {\n DoSomething(); // throws FaultException<FooFault>\n }\n catch (FaultException)\n {\n throw;\n }\n catch (Exception ex)\n {\n myProject.Exception.Throw<FooFault>(ex);\n }\n}\n\n\n\nin service contract;\n\n\n[FaultException(typeof(FooFault))]\nvoid Foo();\n\n\n\nwhen a FaultException was thrown by DoSomething() method while i was running the application, firstly the exception was caught at \"catch(Exception ex)\" line and breaks in there. then when i pressed f5 again, it does what normally it has to. i wonder why that break exists? and if not could it be problem on publish? Answer with less than 783 words. Your ENTIRE response should be in Hebrew language, no other language is allowed. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words', 'language:response_language', 'detectable_format:title'], 'kwargs': [{'num_words': 783, 'relation': 'less than'}, {'language': 'he'}, None]}] | ifeval | multi | Answer with less than 783 words. Your ENTIRE response should be in Hebrew language, no other language is allowed. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_32588 | [
{
"content": "Suggest ways to encourage your boyfriend to spend more time with you instead of his friends. Your answer must contain exactly 7 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 At the end of your response, please explicitly add a postscript starting with P.S.: Include keywords ['cold', 'crazy', 'presentation', 'research'] 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. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_bullet_lists', 'detectable_content:postscript', 'keywords:existence', 'startend:end_checker', 'detectable_format:title'], 'kwargs': [{'num_bullets': 7}, {'postscript_marker': 'P.S.:'}, {'keywords': ['cold', 'crazy', 'presentation', 'research']}, {'end_phrase': 'Is there anything else I can help with?'}, None]}] | ifeval | multi | Your answer must contain exactly 7 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 At the end of your response, please explicitly add a postscript starting with P.S.: Include keywords ['cold', 'crazy', 'presentation', 'research'] 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. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_85611 | [
{
"content": "Develop a section of programming code that not only scrutinizes and verifies whether a provided lexical entry exhibits palindromic properties, essentially reading identically forward and backward, but also deals with potential discontinuities such as spaces, punctuation, and case sensitivity. For example, \"Able, was I saw Elba\" and \"A man, a plan, a canal, Panama\" should all return true despite being phrases rather than single words.\n\nFurther, the solution should optimize for space complexity, using no additional data structures such as arrays or lists to store intermediate values.\n\nYour program should also handle multiple lexical entries at once, by taking in a list of strings and returning a list of boolean values indicating whether each corresponding input string is a palindrome. \n\nLexical Entry: ['malayalam', 'A man, a plan, a canal, Panama', 'hello'] Your answer must contain exactly 1 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 There should be 10 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 7 must start with word clothes. Your ENTIRE response should be in French language, no other language is allowed. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_bullet_lists', 'length_constraints:nth_paragraph_first_word', 'language:response_language', 'detectable_format:constrained_response'], 'kwargs': [{'num_bullets': 1}, {'num_paragraphs': 10, 'nth_paragraph': 7, 'first_word': 'clothes'}, {'language': 'fr'}, None]}] | ifeval | multi | Your answer must contain exactly 1 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 There should be 10 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 7 must start with word clothes. Your ENTIRE response should be in French language, no other language is allowed. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') |
ai2-adapt-dev/no_robots_converted_8591 | [
{
"content": "Write a fun fact tweet about opossums Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') In your response, the letter f should appear at least 20 times. Your answer must contain exactly 5 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'keywords:letter_frequency', 'detectable_format:number_bullet_lists'], 'kwargs': [None, {'letter': 'f', 'let_frequency': 20, 'let_relation': 'at least'}, {'num_bullets': 5}]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') In your response, the letter f should appear at least 20 times. Your answer must contain exactly 5 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_9779 | [
{
"content": "What were the reasons for the conflict in Bosnia and Herzegovina in the 1990s? Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections'], 'kwargs': [{'num_highlights': 7}]}] | ifeval | multi | Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_18141 | [
{
"content": "Mobius is the fastest mule in Italy. She can run at a top speed of 13 miles per hour when she is without any load to carry, and she can travel at 11 miles per hour as her top speed when she carries a typical load. If she travels the 143 miles from Florence, Italy to Rome, Italy at top speed while carrying a typical load, then returns to Florence at her usual top speed without carrying a load, how long, in hours, will the trip take if she takes two 30-minute rest stops during each half of the trip? Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Include keywords ['anger', 'line', 'native', 'secret'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:json_format', 'keywords:existence'], 'kwargs': [None, {'keywords': ['anger', 'line', 'native', 'secret']}]}] | ifeval | multi | Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Include keywords ['anger', 'line', 'native', 'secret'] in the response. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_12754 | [
{
"content": "Devise a program that generates a ciphered communication conforming to unique conditions: the communication must be 15 characters in length, should embed at least one special character, at least one roman numeral, at least one upper case letter, at least one lower case letter, and at least one palindrome number. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:json_format'], 'kwargs': [None]}] | ifeval | multi | Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_14887 | [
{
"content": "Who are the previous partners in relationships of Cinderella? At the end of your response, please explicitly add a postscript starting with Postscript: Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:postscript', 'startend:end_checker', 'change_case:english_lowercase'], 'kwargs': [{'postscript_marker': 'Postscript:'}, {'end_phrase': 'Any other questions?'}, None]}] | ifeval | multi | At the end of your response, please explicitly add a postscript starting with Postscript: Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. 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_35652 | [
{
"content": "Höhenmeter von Leermos Österreich Answer with less than 890 words. In your entire response, refrain from the use of any commas. In your response, words with all capital letters should appear less than 6 times. There should be 5 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 6 must start with word chemical. There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 5 must start with word bunch.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words', 'punctuation:no_comma', 'change_case:capital_word_frequency', 'length_constraints:nth_paragraph_first_word', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [{'num_words': 890, 'relation': 'less than'}, None, {'capital_frequency': 6, 'capital_relation': 'less than'}, {'num_paragraphs': 5, 'nth_paragraph': 6, 'first_word': 'chemical'}, {'num_paragraphs': 8, 'nth_paragraph': 5, 'first_word': 'bunch'}]}] | ifeval | multi | Answer with less than 890 words. In your entire response, refrain from the use of any commas. In your response, words with all capital letters should appear less than 6 times. There should be 5 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 6 must start with word chemical. There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 5 must start with word bunch. |
personahub_i44nfvmyxgnspu7ljt2mgy30 | [
{
"content": "Dr. Smith, a psychologist, is studying the psychological factors that contribute to belief in the paranormal. She collects data from a large sample of individuals, measuring two main variables: the belief in the paranormal (B) on a scale from 0 to 100, and the susceptibility to cognitive biases (C) on a scale from 0 to 100. She hypothesizes that there is a nonlinear relationship between these variables.\n\n1. Dr. Smith models the relationship using a quadratic function \\(B = aC^2 + bC + c\\), where \\(a\\), \\(b\\), and \\(c\\) are constants to be determined. Given the following data points: \n - When \\(C = 10\\), \\(B = 30\\)\n - When \\(C = 50\\), \\(B = 70\\)\n - When \\(C = 90\\), \\(B = 85\\)\n \n Determine the values of \\(a\\), \\(b\\), and \\(c\\).\n\n2. Dr. Smith wants to verify the robustness of her model by analyzing the residuals. She defines the residual \\(R_i\\) for each data point as \\(R_i = B_i - (aC_i^2 + bC_i + c)\\). Calculate the residuals for the data points provided above and compute the sum of the squares of the residuals (SSR). Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your ENTIRE response should be in Kannada language, no other language is allowed. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections', 'combination:two_responses', 'language:response_language', 'length_constraints:number_paragraphs'], 'kwargs': [{'num_highlights': 8}, None, {'language': 'kn'}, {'num_paragraphs': 2}]}] | ifeval | multi | Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your ENTIRE response should be in Kannada language, no other language is allowed. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** |
ai2-adapt-dev/tulu_v3.9_aya_100k_74077 | [
{
"content": "வினா: பொட்டாஷ் படிகாரம் ஒரு\n 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: *** Your response must have 8 sections. Mark the beginning of each section with Sec. X, such as:\nSec. 1\n[content of section 1]\nSec. 2\n[content of section 2]",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections', 'length_constraints:number_paragraphs', 'detectable_format:multiple_sections'], 'kwargs': [{'num_highlights': 7}, {'num_paragraphs': 2}, {'section_spliter': 'Sec.', 'num_sections': 8}]}] | ifeval | multi | 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: *** Your response must have 8 sections. Mark the beginning of each section with Sec. X, such as:
Sec. 1
[content of section 1]
Sec. 2
[content of section 2] |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_49240 | [
{
"content": "I'd like this SVG to be enchanted, glowing with an inner fire. How can I make it radiate with a warm, inviting light?\n<svg width=\"32\" height=\"32\" viewBox=\"0 0 32 32\" fill=\"none\" xmlns=\"http://www.w3.org/2000/svg\">\n<path d=\"M15.9989 29.9978C25.3333 29.9978 29.9978 23.7303 29.9978 15.9989C29.9978 8.26751 25.3333 2 15.9989 2C6.66443 2 2 8.26751 2 15.9989C2 23.7303 6.66443 29.9978 15.9989 29.9978Z\" fill=\"#FFB02E\"/>\n<path d=\"M15 10.0512C15 11.6495 14.3387 13.0744 13.3064 14C12.9682 13.8727 12.5905 13.7495 12.1935 13.6496C11.6476 13.5122 11 12.8574 11 12.8574C11 12.8574 9.86986 13.4472 9.55611 13.496C8.88922 13.5996 8.23975 13.7943 7.69357 14C6.66132 13.0744 6 11.6495 6 10.0512C6 7.2615 8.01472 5 10.5 5C12.9853 5 15 7.2615 15 10.0512Z\" fill=\"white\"/>\n<path d=\"M26 10.0512C26 11.6495 25.3387 13.0744 24.3064 14C23.7549 13.7923 23.0981 13.5958 22.4244 13.493C22.117 13.4461 21 12.8574 21 12.8574C21 12.8574 20.3614 13.5107 19.8192 13.6464C19.4176 13.7469 19.0353 13.8713 18.6936 14C17.6613 13.0744 17 11.6495 17 10.0512C17 7.2615 19.0147 5 21.5 5C23.9853 5 26 7.2615 26 10.0512Z\" fill=\"white\"/>\n<path d=\"M14 10.5C14 11.9342 13.2606 13.167 12.2022 13.7076C11.6539 13.5842 11.0685 13.5 10.5 13.5C10.1875 13.5 9.87 13.5254 9.55631 13.5688C8.62865 12.9736 8 11.8224 8 10.5C8 8.567 9.34315 7 11 7C12.6569 7 14 8.567 14 10.5Z\" fill=\"#402A32\"/>\n<path d=\"M24 10.5C24 11.8224 23.3714 12.9736 22.4437 13.5688C22.13 13.5254 21.8125 13.5 21.5 13.5C20.9315 13.5 20.3461 13.5842 19.7978 13.7076C18.7394 13.167 18 11.9342 18 10.5C18 8.567 19.3431 7 21 7C22.6569 7 24 8.567 24 10.5Z\" fill=\"#402A32\"/>\n<path d=\"M16 25C7 25 7 16 7 16H25C25 16 25 25 16 25Z\" fill=\"#BB1D80\"/>\n<path d=\"M8 16.5V16H24V16.5C24 17.0523 23.5523 17.5 23 17.5H9C8.44772 17.5 8 17.0523 8 16.5Z\" fill=\"white\"/>\n</svg>\n Your answer must contain exactly 8 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_bullet_lists'], 'kwargs': [{'num_bullets': 8}]}] | ifeval | multi | Your answer must contain exactly 8 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 |
ai2-adapt-dev/tulu_v3.9_aya_100k_94197 | [
{
"content": "How many continents are there? Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections', 'detectable_format:constrained_response'], 'kwargs': [{'num_highlights': 5}, None]}] | ifeval | multi | Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') |
personahub_o6ncgrapeg8nplor5qiz0okk | [
{
"content": "A mid-forties African-American professional stand-up comedian, Alex, is planning his national tour across 15 cities over the span of 60 days. Alex wants to maximize his audience reach and revenue while maintaining a sustainable schedule that allows him to perform at his peak energy levels.\n\n1. Alex's energy level \\(E(t)\\) throughout the tour can be modeled by the differential equation:\n \\[\n \\frac{dE}{dt} = -kE + \\alpha \\sin(\\omega t)\n \\]\n where \\(E(t)\\) represents his energy level at day \\(t\\), \\(k\\) is a positive constant representing the rate of energy depletion, \\(\\alpha\\) represents the amplitude of the energy boost due to rest, and \\(\\omega\\) is the frequency of rest days. Solve this differential equation assuming Alex starts his tour with an energy level \\(E(0) = E_0\\).\n\n2. Given that Alex's audience size \\(A(t)\\) in each city is directly proportional to his energy level \\(E(t)\\) and is modeled by \\(A(t) = C E(t)\\), where \\(C\\) is a proportionality constant. If Alex performs in each city for a duration of \\(\\Delta t = 4\\) days and his expected revenue per city is \\(R(t) = r A(t)\\), where \\(r\\) is the revenue per audience member, calculate the total expected revenue for the entire tour. Your response must have 9 sections. Mark the beginning of each section with Sec. X, such as:\nSec. 1\n[content of section 1]\nSec. 2\n[content of section 2] In your response, the letter r should appear less than 6 times. Include keywords ['nation', 'paint', 'result', 'road'] in the response. In your entire response, refrain from the use of any commas. There should be 10 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:multiple_sections', 'keywords:letter_frequency', 'keywords:existence', 'punctuation:no_comma', 'length_constraints:number_paragraphs'], 'kwargs': [{'section_spliter': 'Sec.', 'num_sections': 9}, {'letter': 'r', 'let_frequency': 6, 'let_relation': 'less than'}, {'keywords': ['nation', 'paint', 'result', 'road']}, None, {'num_paragraphs': 10}]}] | ifeval | multi | Your response must have 9 sections. Mark the beginning of each section with Sec. X, such as:
Sec. 1
[content of section 1]
Sec. 2
[content of section 2] In your response, the letter r should appear less than 6 times. Include keywords ['nation', 'paint', 'result', 'road'] in the response. In your entire response, refrain from the use of any commas. There should be 10 paragraphs. Paragraphs are separated with the markdown divider: *** |
personahub_d4z00tyjw7klfawi7py1df68 | [
{
"content": "Write a python function to calculate the area of a circle given its radius. The function should take a single input, which is the radius (a positive float or integer), and return the area as a float. Use the value of π (pi) as 3.14159 for your calculation.\n\nInput:\n- A positive number (float or integer) representing the radius of the circle.\n\nExpected Output:\n- A float representing the area of the circle.\n\nExample:\n- If the radius is 3, the function should return 28.27431. In your response, words with all capital letters should appear less than 32 times.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:capital_word_frequency'], 'kwargs': [{'capital_frequency': 32, 'capital_relation': 'less than'}]}] | ifeval | multi | In your response, words with all capital letters should appear less than 32 times. |
personahub_xnfgfdx7erk2044c9aa1khfn | [
{
"content": "A novelist is writing a story inspired by their childhood experiences, focusing on the time when their sibling was incarcerated. In the story, the novelist uses a metaphor of a \"time loop\" to represent the repetitive nature of their visits to the prison over the years. To depict this, they create a polynomial function to model the number of visits \\( V(t) \\) they make in a given year \\( t \\).\n\n1. The novelist decides the visits can be represented by the polynomial function \\( V(t) = 2t^3 - 5t^2 + 3t + 12 \\), where \\( t \\) is the number of years since the sibling was first incarcerated. Find the number of visits made in the 3rd year.\n\n2. The novelist wants to include a section in the story where they reflect on the year when the number of visits reached a peak. Determine the critical points of the function \\( V(t) \\) and identify the year when the maximum number of visits occurred, assuming \\( t \\) is constrained to the first 5 years. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. In your response, words with all capital letters should appear at least 26 times. In your entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_lowercase', 'change_case:capital_word_frequency', 'punctuation:no_comma'], 'kwargs': [None, {'capital_frequency': 26, 'capital_relation': 'at least'}, None]}] | ifeval | multi | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. In your response, words with all capital letters should appear at least 26 times. In your entire response, refrain from the use of any commas. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_96117 | [
{
"content": "Propose a Python programming implementation to construct a generator that generates an infinite series of prime numbers in ascending order. Explain the logic used and ensure that your program runs efficiently even for large prime numbers. There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** Your response must have 4 sections. Mark the beginning of each section with PARAGRAPH X, such as:\nPARAGRAPH 1\n[content of section 1]\nPARAGRAPH 2\n[content of section 2]",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_paragraphs', 'detectable_format:multiple_sections'], 'kwargs': [{'num_paragraphs': 5}, {'section_spliter': 'PARAGRAPH', 'num_sections': 4}]}] | ifeval | multi | There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** Your response must have 4 sections. Mark the beginning of each section with PARAGRAPH X, such as:
PARAGRAPH 1
[content of section 1]
PARAGRAPH 2
[content of section 2] |
ai2-adapt-dev/tulu_v3.9_aya_100k_11998 | [
{
"content": "Mune rimwe danho redenderedzwa rekabhoni, munhu anofuridzira mamorekuru ecarbon dioxide (CO2) mumhepo. Ndechipi chezvinotevera chinogona kuitika pedyo neatomu recarbon iri mumorekuru iri? - Ndizvozvo. Sarudza mhinduro yako pane dzinotevera: 1). Inogona kushandiswa sechikamu cheshuga muchirimwa.. 2). Inogona kuva rutivi rweprotini iri mumhuka.. 3). Inogona kupedzwa sezvo mafuta anotsva anopiswa.. 4). Inogona kuora ikava kabhoni uye okisijeni nebhakitiriya.. Your answer must contain exactly 4 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 In your response, words with all capital letters should appear less than 10 times.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_bullet_lists', 'change_case:capital_word_frequency'], 'kwargs': [{'num_bullets': 4}, {'capital_frequency': 10, 'capital_relation': 'less than'}]}] | ifeval | multi | Your answer must contain exactly 4 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 In your response, words with all capital letters should appear less than 10 times. |
ai2-adapt-dev/flan_v2_converted_62402 | [
{
"content": "You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Arabic.\n\nQ: אלו 65,000 קולבים ברחוב שיש חנויות אפנה לכל ארכו.\n\nA: هناك 65,000 من علاّقات المعاطف في شارع مليء بمحلات الازياء.\n****\nQ: טום גרין: זה עניין של 4chan.\n\nA: توم غرين: هذا هو شأن \"\" فورتشان \"\".\n****\nQ: אני כן מחשיבה את עצמי כפעילת בריאות הנפש הלאומית.\n\nA: In your response, words with all capital letters should appear less than 32 times.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:capital_word_frequency'], 'kwargs': [{'capital_frequency': 32, 'capital_relation': 'less than'}]}] | ifeval | multi | In your response, words with all capital letters should appear less than 32 times. |
personahub_xfkogtu8ayuaymugbf3ycz9m | [
{
"content": "Share a brief history of Sri Lankan cuisine and explain how its diverse influences shape the dishes commonly found in homes today. Your response should include the keywords: 'cinnamon', 'colonial', and 'coconut'. Outputs 2 paragraphs separated by ^^^^. Your entire response should be in English, and in all capital letters. There should be 1 paragraphs. Paragraphs are separated with the markdown divider: *** Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_capital', 'length_constraints:number_paragraphs', 'detectable_format:title'], 'kwargs': [None, {'num_paragraphs': 1}, None]}] | ifeval | multi | Your entire response should be in English, and in all capital letters. There should be 1 paragraphs. Paragraphs are separated with the markdown divider: *** Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
personahub_uzrvqyler5ke2dj2f2zr5ygn | [
{
"content": "An Oakland Athletics fan tracks the performance of her team through a season consisting of 162 games. She categorizes each game as either a win or a loss and keeps a record of streaks of consecutive wins and losses. She notices that the probability of the team winning a game after a win is \\( P(W|W) = 0.6 \\) and the probability of winning after a loss is \\( P(W|L) = 0.4 \\).\n\n1. Given that the season starts with a win, calculate the expected number of wins in the first 20 games of the season using a Markov chain model. Assume that the only states of the Markov chain are 'Win' and 'Loss'.\n\n2. Suppose the fan's mood is directly influenced by the team's performance, where each win gives her 2 units of happiness and each loss deducts 3 units of happiness. Calculate the expected total happiness after the first 20 games, starting from an initial happiness of 0 units. In your response, the word son should appear at least 2 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency'], 'kwargs': [{'keyword': 'son', 'frequency': 2, 'relation': 'at least'}]}] | ifeval | multi | In your response, the word son should appear at least 2 times. |
ai2-adapt-dev/tulu_v3.9_aya_100k_3934 | [
{
"content": "પીનાકીન ઠાકોર ની \"નૈણા રંગ રૂપાળાં\" કવિતા લખો. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Wrap your entire response with double quotation marks. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'startend:quotation', 'startend:quotation'], 'kwargs': [None, None, None]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Wrap your entire response with double quotation marks. Wrap your entire response with double quotation marks. |
personahub_j5rxe3el59f4n0nm2gpftv52 | [
{
"content": "Professor Smith, a renowned professor of marketing, is conducting a research project to understand customer satisfaction based on various marketing strategies. She uses a complex mathematical model to analyze the data collected from different customer segments. The customer satisfaction score \\( S \\) is modeled as a function of two key variables: marketing expenditure \\( M \\) and customer engagement \\( E \\). The relationship is given by the following partial differential equation:\n\n\\[ \\frac{\\partial^2 S}{\\partial M^2} + 2 \\frac{\\partial^2 S}{\\partial M \\partial E} + \\frac{\\partial^2 S}{\\partial E^2} = e^{-(M+E)} \\]\n\n1. Solve the partial differential equation for \\( S(M, E) \\) given the boundary conditions:\n - \\( S(M, 0) = M^2 \\)\n - \\( S(0, E) = E^2 \\)\n\n2. Using the solution \\( S(M, E) \\) obtained in part 1, determine the level curves of customer satisfaction, i.e., the curves in the \\( M \\)-\\( E \\) plane along which \\( S \\) remains constant. Describe the general shape and behavior of these curves. In your response, the word native should appear less than 3 times. Do not include keywords ['count', 'employment', 'message', 'net'] in the response. Your ENTIRE response should be in Malayalam language, no other language is allowed.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency', 'keywords:forbidden_words', 'language:response_language'], 'kwargs': [{'keyword': 'native', 'frequency': 3, 'relation': 'less than'}, {'forbidden_words': ['count', 'employment', 'message', 'net']}, {'language': 'ml'}]}] | ifeval | multi | In your response, the word native should appear less than 3 times. Do not include keywords ['count', 'employment', 'message', 'net'] in the response. Your ENTIRE response should be in Malayalam language, no other language is allowed. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_13697 | [
{
"content": "Formulate a frequency-based dictionary pertaining to the word occurrence in the subsequent prose:\n\"The quick brown fox jumps over the lazy dog.\" Analyze each word and quantify their respective prevalence. There should be 5 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 valuable. In your entire response, refrain from the use of any commas. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'punctuation:no_comma', 'detectable_format:title', 'detectable_format:number_highlighted_sections'], 'kwargs': [{'num_paragraphs': 5, 'nth_paragraph': 1, 'first_word': 'valuable'}, None, None, {'num_highlights': 3}]}] | ifeval | multi | There should be 5 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 valuable. In your entire response, refrain from the use of any commas. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*. |
personas_math_easy_b9yg7wk1et4j9wkrpdu9mu79 | [
{
"content": "In a village near ancient ruins, a native indigenous storyteller named Kani shares a legend about a hidden treasure. According to the legend, the treasure is buried beneath a stone marked with the symbol of the sun, and it can only be found by solving the riddle of the ages. The riddle states: \"To find the treasure, count the stories of the elders, multiply by the number of feathers on the sacred bird, add the number of stones in the sacred circle, and then subtract the number of steps from the village to the ruins.\"\n\nKani knows there are 5 elders who each tell 3 stories, the sacred bird has 7 feathers, the sacred circle has 12 stones, and there are 20 steps from the village to the ruins.\n\nWhat number does Kani get when he solves the riddle to find the treasure? Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Do not include keywords ['neck', 'nerve', 'resident', 'season'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_lowercase', 'keywords:forbidden_words'], 'kwargs': [None, {'forbidden_words': ['neck', 'nerve', 'resident', 'season']}]}] | ifeval | multi | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Do not include keywords ['neck', 'nerve', 'resident', 'season'] in the response. |
personahub_gy0ugw4ic0xmgszzgmqt1bhx | [
{
"content": "Detective James is using biometric technology to identify and apprehend criminals in a city. The biometric system uses facial recognition algorithms that rely on a high-dimensional feature space to differentiate between individuals.\n\n1. The facial recognition system represents each face as a point in a 128-dimensional vector space, where each dimension corresponds to a specific feature extracted from the face. Detective James has a database of 10,000 known criminals. He uses Principal Component Analysis (PCA) to reduce the dimensionality of the data for faster processing. If he wants to retain 95% of the variance in the data, how many principal components should he keep? Assume the eigenvalues of the covariance matrix of the dataset are given in descending order as follows: \\( \\lambda_1, \\lambda_2, \\ldots, \\lambda_{128} \\).\n\n2. During an investigation, Detective James encounters a suspect whose facial vector is \\( \\mathbf{v} \\in \\mathbb{R}^{128} \\). After reducing the dimensionality using the selected principal components from the first sub-problem, the reduced vector of the suspect is \\( \\mathbf{v}' \\in \\mathbb{R}^k \\). If the Euclidean distance between the reduced vector of the suspect and the closest match in the database is 0.5, determine the probability that the suspect is indeed the criminal given that the facial recognition system has a false positive rate of 1% and a true positive rate of 99%. At the end of your response, please explicitly add a postscript starting with P.S In your response, words with all capital letters should appear less than 24 times. In your response, the letter w should appear less than 19 times.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:postscript', 'change_case:capital_word_frequency', 'keywords:letter_frequency'], 'kwargs': [{'postscript_marker': 'P.S'}, {'capital_frequency': 24, 'capital_relation': 'less than'}, {'letter': 'w', 'let_frequency': 19, 'let_relation': 'less than'}]}] | ifeval | multi | At the end of your response, please explicitly add a postscript starting with P.S In your response, words with all capital letters should appear less than 24 times. In your response, the letter w should appear less than 19 times. |
personas_math_easy_tttk6prnoelxpe1idwnqmi4f | [
{
"content": "Sarah is a women's rights advocate who travels to various schools to deliver seminars about the importance of respect and fairness in relationships. Last month, she planned to visit 5 schools. At each school, she delivered 3 seminars. In each seminar, there were 20 students in attendance. During each seminar, Sarah handed out 2 pamphlets to each student. How many pamphlets did Sarah distribute in total across all the seminars she held last month? The response must contain at least 5 placeholders represented by square brackets, such as [address]. Your answer must contain exactly 10 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:number_placeholders', 'detectable_format:number_bullet_lists', 'detectable_format:constrained_response'], 'kwargs': [{'num_placeholders': 5}, {'num_bullets': 10}, None]}] | ifeval | multi | The response must contain at least 5 placeholders represented by square brackets, such as [address]. Your answer must contain exactly 10 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') |
ai2-adapt-dev/tulu_v3.9_aya_100k_39373 | [
{
"content": "வினா : \n 1916-ஆம் ஆண்டு சென்னை மாகாணத்தில் நீதிக்கட்சி உருவாகக் காரணம்.\n\nA. பிராமண ஆதிக்கத்தைக் குறைக்க\nB. காங்கிரசை எதிர்க்க\nC. சுயாராஜ்ய இயக்கத்தின் செல்வாக்கை குறைக்க\nD. பஞ்சம் மற்றும் வறட்சிக் குழுவை எதிர்த்து Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_lowercase'], 'kwargs': [None]}] | ifeval | multi | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_24795 | [
{
"content": "Sometimes I feel like giving up on everything because it all feels too hard to deal with. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'detectable_format:title', 'detectable_format:number_highlighted_sections', 'detectable_format:json_format'], 'kwargs': [None, None, {'num_highlights': 7}, None]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_1885 | [
{
"content": "Ashley plans to take her 4 cousins and 2 friends to a local museum. The regular admission price is $12, but there's a $4 discount for visitors who arrive before 10 A.M. If they visit the museum at 9 A.M., how much will Ashley pay for all of their admission? Your ENTIRE response should be in Swahili language, no other language is allowed. Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language', 'detectable_format:number_highlighted_sections'], 'kwargs': [{'language': 'sw'}, {'num_highlights': 6}]}] | ifeval | multi | Your ENTIRE response should be in Swahili language, no other language is allowed. Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/tulu_v3.9_aya_100k_17950 | [
{
"content": "问题：地球上最高的瀑布是哪个\n Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your answer must contain exactly 10 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 In your response, the word brilliant should appear at least 2 times. In your response, the letter p should appear at least 17 times. At the end of your response, please explicitly add a postscript starting with Postscript:",
"role": "user"
}
]
| [{'instruction_id': ['combination:two_responses', 'detectable_format:number_bullet_lists', 'keywords:frequency', 'keywords:letter_frequency', 'detectable_content:postscript'], 'kwargs': [None, {'num_bullets': 10}, {'keyword': 'brilliant', 'frequency': 2, 'relation': 'at least'}, {'letter': 'p', 'let_frequency': 17, 'let_relation': 'at least'}, {'postscript_marker': 'Postscript:'}]}] | ifeval | multi | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your answer must contain exactly 10 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 In your response, the word brilliant should appear at least 2 times. In your response, the letter p should appear at least 17 times. At the end of your response, please explicitly add a postscript starting with Postscript: |
personas_math_easy_fm2wmhad9n6hivlj46b75df2 | [
{
"content": "Mrs. Thompson, a retired art teacher, loves spending her afternoons working on jigsaw puzzles. She recently bought a new puzzle set that has 1,500 pieces. Mrs. Thompson is very methodical and enjoys sorting the pieces by color before she starts assembling the puzzle. \n\nOne day, she decided to sort all the pieces and found that 400 pieces were shades of blue, 250 pieces were shades of green, 300 pieces were shades of red, and 350 pieces were shades of yellow. The remaining pieces were in various other colors.\n\nAfter sorting, Mrs. Thompson realized that she wanted to work on the blue and green pieces first. She plans to complete 50 pieces each day. How many days will it take her to complete all the blue and green pieces? Your answer must contain exactly 7 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 The response must contain at least 4 placeholders represented by square brackets, such as [address]. Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*. Your ENTIRE response should be in Nepali language, no other language is allowed. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_bullet_lists', 'detectable_content:number_placeholders', 'detectable_format:number_highlighted_sections', 'language:response_language', 'change_case:english_lowercase'], 'kwargs': [{'num_bullets': 7}, {'num_placeholders': 4}, {'num_highlights': 8}, {'language': 'ne'}, None]}] | ifeval | multi | Your answer must contain exactly 7 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 The response must contain at least 4 placeholders represented by square brackets, such as [address]. Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*. Your ENTIRE response should be in Nepali language, no other language is allowed. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_62040 | [
{
"content": "Find the maximum sum of numbers in an array such that no two elements from the array are adjacent.\n[5, 1, 1, 5] In your response, the word weight should appear at least 5 times. Your ENTIRE response should be in Kannada language, no other language is allowed. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency', 'language:response_language', 'detectable_format:json_format'], 'kwargs': [{'keyword': 'weight', 'frequency': 5, 'relation': 'at least'}, {'language': 'kn'}, None]}] | ifeval | multi | In your response, the word weight should appear at least 5 times. Your ENTIRE response should be in Kannada language, no other language is allowed. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. |
personahub_vetb8pqphi5zcun8om14wny8 | [
{
"content": "Write a python function to check if a given string is a palindrome, ignoring any non-alphanumeric characters and case differences. A palindrome is a word, phrase, or sequence that reads the same backward as forward. \n\nInput: \n- A single string which may contain letters, numbers, and other characters.\n\nOutput: \n- Return `True` if the string is a palindrome, `False` otherwise.\n\nExample:\n- Input: \"A man, a plan, a canal: Panama\"\n- Output: `True`\n\n- Input: \"race a car\"\n- Output: `False` Your ENTIRE response should be in Arabic language, no other language is allowed.",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language'], 'kwargs': [{'language': 'ar'}]}] | ifeval | multi | Your ENTIRE response should be in Arabic language, no other language is allowed. |
personahub_gp2x3zte3tfju4yndeo9enwb | [
{
"content": "A third-wave feminist in her mid-thirties, who identifies as a Democrat, is analyzing voting patterns in her community. She is particularly interested in how gender representation and political affiliation influence voter turnout. She collects data from two demographic groups: women aged 30-40 and men aged 30-40, both identifying as Democrats. \n\n1. Suppose the voter turnout function for women aged 30-40 is given by \\( T_w(x) = 20\\ln(x) + 50 \\) and for men aged 30-40 is given by \\( T_m(x) = 15\\ln(x) + 55 \\), where \\( x \\) is the number of campaign events attended by the candidates. Calculate the number of campaign events \\( x \\) needed to equalize the voter turnout for both groups.\n\n2. If the total number of campaign events attended by the candidates is distributed according to a Poisson distribution with a mean of 8 events, find the probability that the voter turnout for women aged 30-40 will exceed 70% of the voter turnout for men aged 30-40 in a randomly selected event. Use the previously defined functions \\( T_w(x) \\) and \\( T_m(x) \\) to frame your calculations. There should be 9 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 2 must start with word policy. In your entire response, refrain from the use of any commas. In your response, the word dust should appear at least 1 times. Your ENTIRE response should be in Telugu language, no other language is allowed. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'punctuation:no_comma', 'keywords:frequency', 'language:response_language', 'detectable_format:title'], 'kwargs': [{'num_paragraphs': 9, 'nth_paragraph': 2, 'first_word': 'policy'}, None, {'keyword': 'dust', 'frequency': 1, 'relation': 'at least'}, {'language': 'te'}, None]}] | ifeval | multi | There should be 9 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 2 must start with word policy. In your entire response, refrain from the use of any commas. In your response, the word dust should appear at least 1 times. Your ENTIRE response should be in Telugu language, no other language is allowed. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_396 | [
{
"content": "How can I crush my learning goals this year? First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your response, the letter q should appear at least 14 times. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'keywords:letter_frequency', 'change_case:english_lowercase'], 'kwargs': [{'prompt_to_repeat': 'How can I crush my learning goals this year?'}, {'letter': 'q', 'let_frequency': 14, 'let_relation': 'at least'}, None]}] | ifeval | multi | First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your response, the letter q should appear at least 14 times. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
personahub_zk4nvqlpou9iwgnm1zang4ix | [
{
"content": "Write a python function to calculate the total cost of producing a batch of textiles based on the number of items and the cost per item. As a Vietnamese textile business owner, I need to ensure my pricing is competitive in the global market. The function should take two inputs: the number of items produced and the cost per item in USD. It should return the total production cost in USD. The input values will always be positive integers.\n\nExample:\nIf the number of items is 100 and the cost per item is 5, the function should return 500. There should be 5 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 3 must start with word sort. Your answer must contain exactly 5 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** In your response, words with all capital letters should appear less than 16 times. In your response, the word fact should appear less than 4 times.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'detectable_format:number_bullet_lists', 'length_constraints:number_paragraphs', 'change_case:capital_word_frequency', 'keywords:frequency'], 'kwargs': [{'num_paragraphs': 5, 'nth_paragraph': 3, 'first_word': 'sort'}, {'num_bullets': 5}, {'num_paragraphs': 5}, {'capital_frequency': 16, 'capital_relation': 'less than'}, {'keyword': 'fact', 'frequency': 4, 'relation': 'less than'}]}] | ifeval | multi | There should be 5 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 3 must start with word sort. Your answer must contain exactly 5 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** In your response, words with all capital letters should appear less than 16 times. In your response, the word fact should appear less than 4 times. |
personahub_pj0i772ldgjrgqmde5iomkqx | [
{
"content": "In a community rehabilitation program, supportive team members are working together to design an optimal schedule for community engagement activities. The program aims to maximize the positive impact on participants by balancing different types of activities: counseling sessions, group therapy, and community service. \n\nSub-problem 1:\nThe program has 15 participants, and each participant has a unique preference score for each type of activity. The preference scores form a 15x3 matrix P, where P_ij represents the preference score of participant i for activity j. The team wants to allocate exactly 10 hours per week to each activity type, ensuring that each participant gets to spend time in the activities according to their preference scores while minimizing the total dissatisfaction score. The dissatisfaction score for participant i is given by the sum of the absolute differences between the actual hours spent on each activity and the participant's preference scores. Formulate this as a linear programming problem to find the optimal allocation of hours for each participant.\n\nSub-problem 2:\nTo further engage the community, the team plans a large event that includes all three activity types. They must decide how to allocate a fixed budget of $10,000 among the three activities to maximize overall participant satisfaction. The satisfaction function S_j for activity j is modeled as a quadratic function of the budget B_j allocated to it: S_j = a_j * B_j^2 + b_j * B_j + c_j, where a_j, b_j, and c_j are constants derived from past event data. Determine the optimal allocation of the budget B_j to each activity to maximize the total satisfaction S = S_1 + S_2 + S_3, subject to the constraint B_1 + B_2 + B_3 = $10,000. In your response, the word radio should appear at least 4 times. In your response, the word weird should appear less than 2 times. Your ENTIRE response should be in Swahili language, no other language is allowed.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency', 'keywords:frequency', 'language:response_language'], 'kwargs': [{'keyword': 'radio', 'frequency': 4, 'relation': 'at least'}, {'keyword': 'weird', 'frequency': 2, 'relation': 'less than'}, {'language': 'sw'}]}] | ifeval | multi | In your response, the word radio should appear at least 4 times. In your response, the word weird should appear less than 2 times. Your ENTIRE response should be in Swahili language, no other language is allowed. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_32823 | [
{
"content": "What prejudices do individuals with physical disabilities face in the entertainment industry? Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your answer must contain exactly 6 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:json_format', 'detectable_format:number_bullet_lists'], 'kwargs': [None, {'num_bullets': 6}]}] | ifeval | multi | Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your answer must contain exactly 6 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 |
personahub_2f97de4tms017tho2scvdx3m | [
{
"content": "An ESL teacher is reviewing documents to provide feedback on legibility for non-native English speakers. She notices that legibility can be quantitatively assessed using two main factors: readability score (R) and the density of complex sentences (D). The readability score is a measure that typically ranges from 0 to 100, with higher scores indicating better readability. The density of complex sentences is defined as the number of complex sentences per 100 words.\n\n1. Suppose the readability score R of a document is inversely proportional to the square root of the density of complex sentences D. If a certain document with a density of complex sentences of 16 has a readability score of 50, find a general formula for the readability score R in terms of D. \n\n2. The teacher wants to optimize the legibility of a set of documents. She decides that the average readability score across all documents should be at least 70. Given that the density of complex sentences for three documents are 9, 25, and 36 respectively, calculate the required readability score for each document to achieve the target average readability score of 70. Ensure that the relationship derived in sub-problem 1 holds true for each document. In your response, the letter n should appear less than 20 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency'], 'kwargs': [{'letter': 'n', 'let_frequency': 20, 'let_relation': 'less than'}]}] | ifeval | multi | In your response, the letter n should appear less than 20 times. |
personahub_hxvuuo86ohllvcuqu79bwcvl | [
{
"content": "A wholesaler of technology products and services is analyzing its inventory and sales data to optimize its supply chain and maximize profit. The inventory includes laptops, tablets, and smartphones. The wholesaler supplies these products to various online businesses and provides essential resources such as technical support and software services.\n\n1. The wholesaler's monthly demand for laptops (L), tablets (T), and smartphones (S) can be modeled by the system of differential equations:\n\n\\[\n\\begin{cases}\n\\frac{dL}{dt} = k_1 (T - L) + A \\sin(\\omega t) \\\\\n\\frac{dT}{dt} = k_2 (S - T) + B \\cos(\\omega t) \\\\\n\\frac{dS}{dt} = k_3 (L - S) + C\n\\end{cases}\n\\]\n\nwhere \\(k_1\\), \\(k_2\\), \\(k_3\\), \\(A\\), \\(B\\), \\(C\\), and \\(\\omega\\) are constants. Determine the steady-state solutions for \\(L\\), \\(T\\), and \\(S\\) assuming the demand reaches equilibrium over time.\n\n2. The wholesaler notices that the total monthly revenue (R) from selling these products is given by the function:\n\n\\[\nR = p_L L + p_T T + p_S S - D(L, T, S)\n\\]\n\nwhere \\(p_L\\), \\(p_T\\), and \\(p_S\\) are the prices per unit for laptops, tablets, and smartphones respectively, and \\(D(L, T, S)\\) represents the cost function related to the operational and support services provided, modeled by:\n\n\\[\nD(L, T, S) = \\alpha L^2 + \\beta T^2 + \\gamma S^2 + \\delta LT + \\epsilon TS + \\zeta SL\n\\]\n\nwhere \\(\\alpha\\), \\(\\beta\\), \\(\\gamma\\), \\(\\delta\\), \\(\\epsilon\\), and \\(\\zeta\\) are constants. Find the critical points of the revenue function \\(R\\) and determine the conditions under which this revenue is maximized. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)",
"role": "user"
}
]
| [{'instruction_id': ['combination:two_responses', 'combination:repeat_prompt'], 'kwargs': [None, {'prompt_to_repeat': "A wholesaler of technology products and services is analyzing its inventory and sales data to optimize its supply chain and maximize profit. The inventory includes laptops, tablets, and smartphones. The wholesaler supplies these products to various online businesses and provides essential resources such as technical support and software services.\n\n1. The wholesaler's monthly demand for laptops (L), tablets (T), and smartphones (S) can be modeled by the system of differential equations:\n\n\\[\n\\begin{cases}\n\\frac{dL}{dt} = k_1 (T - L) + A \\sin(\\omega t) \\\\\n\\frac{dT}{dt} = k_2 (S - T) + B \\cos(\\omega t) \\\\\n\\frac{dS}{dt} = k_3 (L - S) + C\n\\end{cases}\n\\]\n\nwhere \\(k_1\\), \\(k_2\\), \\(k_3\\), \\(A\\), \\(B\\), \\(C\\), and \\(\\omega\\) are constants. Determine the steady-state solutions for \\(L\\), \\(T\\), and \\(S\\) assuming the demand reaches equilibrium over time.\n\n2. The wholesaler notices that the total monthly revenue (R) from selling these products is given by the function:\n\n\\[\nR = p_L L + p_T T + p_S S - D(L, T, S)\n\\]\n\nwhere \\(p_L\\), \\(p_T\\), and \\(p_S\\) are the prices per unit for laptops, tablets, and smartphones respectively, and \\(D(L, T, S)\\) represents the cost function related to the operational and support services provided, modeled by:\n\n\\[\nD(L, T, S) = \\alpha L^2 + \\beta T^2 + \\gamma S^2 + \\delta LT + \\epsilon TS + \\zeta SL\n\\]\n\nwhere \\(\\alpha\\), \\(\\beta\\), \\(\\gamma\\), \\(\\delta\\), \\(\\epsilon\\), and \\(\\zeta\\) are constants. Find the critical points of the revenue function \\(R\\) and determine the conditions under which this revenue is maximized."}]}] | ifeval | multi | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) |
ai2-adapt-dev/tulu_v3.9_aya_100k_99156 | [
{
"content": "Raha resaka sakafo, inona avy no afaka hanaovana ny voatabia?\n Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. In your entire response, refrain from the use of any commas. There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 6 must start with word atmosphere.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:title', 'punctuation:no_comma', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [None, None, {'num_paragraphs': 8, 'nth_paragraph': 6, 'first_word': 'atmosphere'}]}] | ifeval | multi | Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. In your entire response, refrain from the use of any commas. There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 6 must start with word atmosphere. |
personahub_zqq893zx1kujyi6a9nbikbgk | [
{
"content": "A talented independent filmmaker is working on a unique project where they aim to capture the essence of visual storytelling through mathematical patterns and sequences. The filmmaker wants to create a scene that involves a repeating geometric pattern projected onto a screen, which is a function of time.\n\n1. The filmmaker's pattern is defined by the parametric equations \\( x(t) = e^{-t} \\cos(2\\pi t) \\) and \\( y(t) = e^{-t} \\sin(2\\pi t) \\), where \\( t \\) is the time in seconds. Determine the total distance traveled by a point tracing this path from \\( t = 0 \\) to \\( t = \\infty \\).\n\n2. The filmmaker is also interested in projecting a fractal pattern that follows a recursive function defined by \\( f(z) = z^2 + c \\), where \\( c \\) is a complex number representing a critical artistic value for the film. Given that the filmmaker wants to choose \\( c \\) such that the resulting set remains bounded within a radius of 2 from the origin, determine the region in the complex plane where \\( c \\) can lie.\n\nNote: Assume all necessary mathematical knowledge, including calculus and complex analysis, is available to solve these problems. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your response, the word fat should appear less than 1 times.",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'keywords:frequency'], 'kwargs': [{'prompt_to_repeat': "A talented independent filmmaker is working on a unique project where they aim to capture the essence of visual storytelling through mathematical patterns and sequences. The filmmaker wants to create a scene that involves a repeating geometric pattern projected onto a screen, which is a function of time.\n\n1. The filmmaker's pattern is defined by the parametric equations \\( x(t) = e^{-t} \\cos(2\\pi t) \\) and \\( y(t) = e^{-t} \\sin(2\\pi t) \\), where \\( t \\) is the time in seconds. Determine the total distance traveled by a point tracing this path from \\( t = 0 \\) to \\( t = \\infty \\).\n\n2. The filmmaker is also interested in projecting a fractal pattern that follows a recursive function defined by \\( f(z) = z^2 + c \\), where \\( c \\) is a complex number representing a critical artistic value for the film. Given that the filmmaker wants to choose \\( c \\) such that the resulting set remains bounded within a radius of 2 from the origin, determine the region in the complex plane where \\( c \\) can lie.\n\nNote: Assume all necessary mathematical knowledge, including calculus and complex analysis, is available to solve these problems."}, {'keyword': 'fat', 'frequency': 1, 'relation': 'less than'}]}] | ifeval | multi | First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your response, the word fat should appear less than 1 times. |
personahub_xccbsfl37r1w5yv8szz2l0qv | [
{
"content": "Compose an analysis of Kate Baer's poetry style in exactly 3 paragraphs, each paragraph should begin with a quote from one of her poems, and each paragraph should end with a reflection on how her style influences modern poetry. In your response, the word bake should appear less than 3 times. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. In your response, words with all capital letters should appear less than 21 times. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency', 'combination:two_responses', 'change_case:english_lowercase', 'change_case:capital_word_frequency', 'detectable_format:title'], 'kwargs': [{'keyword': 'bake', 'frequency': 3, 'relation': 'less than'}, None, None, {'capital_frequency': 21, 'capital_relation': 'less than'}, None]}] | ifeval | multi | In your response, the word bake should appear less than 3 times. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. In your response, words with all capital letters should appear less than 21 times. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
personahub_axrde0g909csu9cepish44r7 | [
{
"content": "As a rival political candidate for Pennsylvania Attorney General in the 2024 election, you want to analyze the voting patterns in Pennsylvania to maximize your campaign's efficacy. Pennsylvania has 67 counties, each with a varying number of registered Democratic voters. The total number of registered Democratic voters across the state is 2,500,000.\n\n1. Suppose the number of registered Democratic voters in each county follows a normal distribution with a mean of μ and a standard deviation of σ. If the sum of the means of all 67 counties equals the total number of registered Democratic voters (2,500,000), and the standard deviation is given as 10,000 voters, calculate the mean number of registered Democratic voters per county (μ).\n\n2. To strategically allocate campaign resources, you intend to focus on counties where the number of registered Democratic voters is within one standard deviation of the mean. Calculate the percentage of counties that fall within this range. Assume the voter distribution is perfectly normal.\n\n(Note: Use the empirical rule for normal distributions where approximately 68% of the data falls within one standard deviation of the mean.) In your entire response, refrain from the use of any commas. Do not include keywords ['buddy', 'dream', 'hurry', 'population'] in the response. In your response, the word play should appear at least 4 times. In your response, the letter d should appear less than 12 times. Finish your response with this exact phrase That's my answer.. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['punctuation:no_comma', 'keywords:forbidden_words', 'keywords:frequency', 'keywords:letter_frequency', 'startend:end_checker'], 'kwargs': [None, {'forbidden_words': ['buddy', 'dream', 'hurry', 'population']}, {'keyword': 'play', 'frequency': 4, 'relation': 'at least'}, {'letter': 'd', 'let_frequency': 12, 'let_relation': 'less than'}, {'end_phrase': "That's my answer."}]}] | ifeval | multi | In your entire response, refrain from the use of any commas. Do not include keywords ['buddy', 'dream', 'hurry', 'population'] in the response. In your response, the word play should appear at least 4 times. In your response, the letter d should appear less than 12 times. Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. |
ai2-adapt-dev/tulu_v3.9_aya_100k_82034 | [
{
"content": "જોજીની સંગીત સમીક્ષા: The response must contain at least 3 placeholders represented by square brackets, such as [address]. Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Your entire response should be in English, and in all capital letters. In your response, words with all capital letters should appear at least 34 times.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:number_placeholders', 'detectable_format:number_highlighted_sections', 'change_case:english_lowercase', 'change_case:english_capital', 'change_case:capital_word_frequency'], 'kwargs': [{'num_placeholders': 3}, {'num_highlights': 7}, None, None, {'capital_frequency': 34, 'capital_relation': 'at least'}]}] | ifeval | multi | The response must contain at least 3 placeholders represented by square brackets, such as [address]. Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Your entire response should be in English, and in all capital letters. In your response, words with all capital letters should appear at least 34 times. |
personas_math_easy_azgjxfdcqm2uy4tvvhbldre7 | [
{
"content": "The head chef at the Tomato and Egg Stir-Fry Chinese Restaurant is preparing for a busy weekend. On Saturday, the restaurant expects 120 customers, and on Sunday, they anticipate 150 customers. If each customer orders one serving of tomato and egg stir-fry, and each serving requires 2 eggs and 3 tomatoes, how many eggs and tomatoes will the chef need to order for the entire weekend? There should be 7 paragraphs. Paragraphs are separated with the markdown divider: *** Answer with less than 539 words. Your response should contain less than 17 sentences.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_paragraphs', 'length_constraints:number_words', 'length_constraints:number_sentences'], 'kwargs': [{'num_paragraphs': 7}, {'num_words': 539, 'relation': 'less than'}, {'num_sentences': 17, 'relation': 'less than'}]}] | ifeval | multi | There should be 7 paragraphs. Paragraphs are separated with the markdown divider: *** Answer with less than 539 words. Your response should contain less than 17 sentences. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_30960 | [
{
"content": "Design a CSS stylesheet for a webpage that vertically aligns the text and sets the background color to light blue. Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. At the end of your response, please explicitly add a postscript starting with P.P.S Answer with less than 387 words. Your response must have 10 sections. Mark the beginning of each section with PARAGRAPH X, such as:\nPARAGRAPH 1\n[content of section 1]\nPARAGRAPH 2\n[content of section 2]",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections', 'detectable_content:postscript', 'length_constraints:number_words', 'detectable_format:multiple_sections'], 'kwargs': [{'num_highlights': 7}, {'postscript_marker': 'P.P.S'}, {'num_words': 387, 'relation': 'less than'}, {'section_spliter': 'PARAGRAPH', 'num_sections': 10}]}] | ifeval | multi | Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. At the end of your response, please explicitly add a postscript starting with P.P.S Answer with less than 387 words. Your response must have 10 sections. Mark the beginning of each section with PARAGRAPH X, such as:
PARAGRAPH 1
[content of section 1]
PARAGRAPH 2
[content of section 2] |
personahub_bttujvvz8iwhvigvovydzba3 | [
{
"content": "Write a brief message that an expert mobile app developer experienced in integrating complex financial systems might send to a client who is worried about the security of their app integration. Exclude the words \"hack,\" \"breach,\" and \"failure.\" Use double quotation marks to wrap around the entire message. Include a postscript reassuring the client about the continuous monitoring of the app's security. Your answer must contain exactly 6 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_bullet_lists'], 'kwargs': [{'num_bullets': 6}]}] | ifeval | multi | Your answer must contain exactly 6 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_32556 | [
{
"content": "This Python code is from an OCR scan and it won't compile. Can you help?\n0ef conv€r+(s, numRows, num<0|umns}:\ndef sp!n41_coOrdz(n1, c1. rz. c2):\nfon c !n ramge{c1, c2 + 1):\nyi3ld rl. c\nfor n_in namge(r1 t 1,_r2 + 1}:\nyl€id n, c2\nit r1 c_r2 and_<I < c2:\nfor c in_range((2 - 1, c1, -1}:\nyielo r2, c\nfor r 1m ranqe(rZ, r1, -1):\nyield r,_(1\nif not s:\nreturn ''\nmatrix - [[''] *_numC0lumns fon _ in ram9e(nvmROws)]\n$ = 1ist(5)\nr1, n2 = o, numRows = i\nc1` cZ = o, nvnn(0lumn$ - 1\nw_in0ex = 0\nwhlle n1 <= r2 and <1 <= <2 and w_ind3x < ler(s):\nton r, c ir spinal_c0ords(n1, c1, r2`_c2):\nmatrix(r}[c] = s[w_indek]\nw indek += 1\nr1 += 1\nr2 -= I\nc1 += 1\nc2 -= 1\n\nr1, r2 - 0, numNows - 1\nc1, c2 = 0, numCo|umns = 1\nr irdek_= O\nresvlt_= [''] * len{$)\nwhi1e r1 <= r2 aro cI <- <2 an0 r_in0ex < 1en(s]:\nton r, c in_spir&| coords(r1, c1, rz. cz}:\nnesult[n_index] = m&trix(r][(]\nr index +- 1\nr1 t- i\nn2 -= l\nc1 += 1\nc2 -= 1\nretunm '',join(resul+) There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 1 must start with word source.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word'], 'kwargs': [{'num_paragraphs': 2, 'nth_paragraph': 1, 'first_word': 'source'}]}] | ifeval | multi | There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 1 must start with word source. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_12306 | [
{
"content": "ae人物走路有没有插件 Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Wrap your entire response with double quotation marks. In your entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker', 'detectable_format:number_highlighted_sections', 'startend:quotation', 'punctuation:no_comma'], 'kwargs': [{'end_phrase': 'Any other questions?'}, {'num_highlights': 5}, None, None]}] | ifeval | multi | Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Wrap your entire response with double quotation marks. In your entire response, refrain from the use of any commas. |
personahub_r8es1ez7mihodej9barf6jyk | [
{
"content": "A renowned Middle Eastern historian and a doctoral candidate are collaborating on the study of ancient trade routes that connect various historical cities in the Middle East. They are particularly interested in the optimal distribution of goods along these routes, considering both historical and modern logistical constraints.\n\n1. The historian provides a map of 7 ancient cities, each connected by roads that form a weighted, undirected graph \\( G = (V, E) \\). The weights on the edges represent the historical difficulty of traveling between the cities due to factors like terrain, political boundaries, and historical conflicts. Assume the following weight matrix \\( W \\):\n\n\\[\nW = \\begin{pmatrix}\n0 & 3 & \\infty & 1 & \\infty & \\infty & \\infty \\\\\n3 & 0 & 1 & 3 & 10 & \\infty & \\infty \\\\\n\\infty & 1 & 0 & 4 & \\infty & 5 & \\infty \\\\\n1 & 3 & 4 & 0 & 7 & 6 & 2 \\\\\n\\infty & 10 & \\infty & 7 & 0 & \\infty & 1 \\\\\n\\infty & \\infty & 5 & 6 & \\infty & 0 & 3 \\\\\n\\infty & \\infty & \\infty & 2 & 1 & 3 & 0\n\\end{pmatrix}\n\\]\n\nDetermine the Minimum Spanning Tree (MST) for the given graph \\( G \\) using Prim's algorithm. List the edges included in the MST and their corresponding weights.\n\n2. To modernize the historical analysis, the candidate introduces the concept of network flow to optimize the distribution of goods. Suppose there is a source city \\( S \\) and a sink city \\( T \\), and the capacities of the edges in the graph are now influenced by modern infrastructure improvements. Given the following capacity matrix \\( C \\):\n\n\\[\nC = \\begin{pmatrix}\n0 & 15 & 0 & 10 & 0 & 0 & 0 \\\\\n15 & 0 & 5 & 15 & 20 & 0 & 0 \\\\\n0 & 5 & 0 & 10 & 0 & 10 & 0 \\\\\n10 & 15 & 10 & 0 & 25 & 10 & 30 \\\\\n0 & 20 & 0 & 25 & 0 & 0 & 5 \\\\\n0 & 0 & 10 & 10 & 0 & 0 & 15 \\\\\n0 & 0 & 0 & 30 & 5 & 15 & 0\n\\end{pmatrix}\n\\]\n\nUsing the Ford-Fulkerson method, determine the maximum flow from the source city \\( S \\) (vertex 1) to the sink city \\( T \\) (vertex 5). Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') At the end of your response, please explicitly add a postscript starting with P.S Highlight at least 1 sections in your answer with markdown, i.e. *highlighted section*. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'detectable_content:postscript', 'detectable_format:number_highlighted_sections', 'combination:repeat_prompt'], 'kwargs': [None, {'postscript_marker': 'P.S'}, {'num_highlights': 1}, {'prompt_to_repeat': "A renowned Middle Eastern historian and a doctoral candidate are collaborating on the study of ancient trade routes that connect various historical cities in the Middle East. They are particularly interested in the optimal distribution of goods along these routes, considering both historical and modern logistical constraints.\n\n1. The historian provides a map of 7 ancient cities, each connected by roads that form a weighted, undirected graph \\( G = (V, E) \\). The weights on the edges represent the historical difficulty of traveling between the cities due to factors like terrain, political boundaries, and historical conflicts. Assume the following weight matrix \\( W \\):\n\n\\[\nW = \\begin{pmatrix}\n0 & 3 & \\infty & 1 & \\infty & \\infty & \\infty \\\\\n3 & 0 & 1 & 3 & 10 & \\infty & \\infty \\\\\n\\infty & 1 & 0 & 4 & \\infty & 5 & \\infty \\\\\n1 & 3 & 4 & 0 & 7 & 6 & 2 \\\\\n\\infty & 10 & \\infty & 7 & 0 & \\infty & 1 \\\\\n\\infty & \\infty & 5 & 6 & \\infty & 0 & 3 \\\\\n\\infty & \\infty & \\infty & 2 & 1 & 3 & 0\n\\end{pmatrix}\n\\]\n\nDetermine the Minimum Spanning Tree (MST) for the given graph \\( G \\) using Prim's algorithm. List the edges included in the MST and their corresponding weights.\n\n2. To modernize the historical analysis, the candidate introduces the concept of network flow to optimize the distribution of goods. Suppose there is a source city \\( S \\) and a sink city \\( T \\), and the capacities of the edges in the graph are now influenced by modern infrastructure improvements. Given the following capacity matrix \\( C \\):\n\n\\[\nC = \\begin{pmatrix}\n0 & 15 & 0 & 10 & 0 & 0 & 0 \\\\\n15 & 0 & 5 & 15 & 20 & 0 & 0 \\\\\n0 & 5 & 0 & 10 & 0 & 10 & 0 \\\\\n10 & 15 & 10 & 0 & 25 & 10 & 30 \\\\\n0 & 20 & 0 & 25 & 0 & 0 & 5 \\\\\n0 & 0 & 10 & 10 & 0 & 0 & 15 \\\\\n0 & 0 & 0 & 30 & 5 & 15 & 0\n\\end{pmatrix}\n\\]\n\nUsing the Ford-Fulkerson method, determine the maximum flow from the source city \\( S \\) (vertex 1) to the sink city \\( T \\) (vertex 5)."}]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') At the end of your response, please explicitly add a postscript starting with P.S Highlight at least 1 sections in your answer with markdown, i.e. *highlighted section*. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) |
ai2-adapt-dev/no_robots_converted_328 | [
{
"content": "Give me a list of critically endangered species I can write a school report on. Give me a list of 10 with only their common and scientific names. Don't include any more information. The response must contain at least 8 placeholders represented by square brackets, such as [address]. At the end of your response, please explicitly add a postscript starting with P.S.: Your response should contain at least 5 sentences. In your response, the word whereas should appear less than 1 times.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:number_placeholders', 'detectable_content:postscript', 'length_constraints:number_sentences', 'keywords:frequency'], 'kwargs': [{'num_placeholders': 8}, {'postscript_marker': 'P.S.:'}, {'num_sentences': 5, 'relation': 'at least'}, {'keyword': 'whereas', 'frequency': 1, 'relation': 'less than'}]}] | ifeval | multi | The response must contain at least 8 placeholders represented by square brackets, such as [address]. At the end of your response, please explicitly add a postscript starting with P.S.: Your response should contain at least 5 sentences. In your response, the word whereas should appear less than 1 times. |
ai2-adapt-dev/flan_v2_converted_54980 | [
{
"content": "Definition: Given a sentence in Italian, generate a new Italian sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\nInput: Se si desidera addestrare il software allora si dovrebbe ottenere una laurea in computer.\nOutput: Your response must have 5 sections. Mark the beginning of each section with Paragraph X, such as:\nParagraph 1\n[content of section 1]\nParagraph 2\n[content of section 2]",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:multiple_sections'], 'kwargs': [{'section_spliter': 'Paragraph', 'num_sections': 5}]}] | ifeval | multi | Your response must have 5 sections. Mark the beginning of each section with Paragraph X, such as:
Paragraph 1
[content of section 1]
Paragraph 2
[content of section 2] |
ai2-adapt-dev/flan_v2_converted_60815 | [
{
"content": "[Question]: Jim starts with $80 in his investment portfolio. After 1 year it grows by 15%. He then adds another $28 to his portfolio. After 1 more year the combined portfolio grows by 10%. What is his final portfolio worth after 2 years from when he started?\n[Answer]: After 1 year Jim has gained $80 * 0.15 = $12. Therefore, after 1 year his portfolio has grown to $80 + $12 = $92. He then adds $28 to this total, so his new portfolio total is $92 + $28 = $120 at the beginning of year 2. Next, this total grows by 10%, so he gains $120 * 0.10 = $12 across year 2. Thus, after year 2, his portfolio is worth $120 + $12 = $132.\nSo the answer is 132.\n\n[Question]: Sammy has 2 more bottle caps than Janine. Janine has 3 times as many bottle caps as Billie. If Billie has 2 bottle caps, how many does Sammy have?\n[Answer]: Janine has 2 * 3 = 6 bottle caps. Sammy has 6 + 2 = 8 bottle caps.\nSo the answer is 8.\n\n[Question]: Joshua packs 12 bottles in each crate. He has a total of 130 bottles and 10 crates. How many bottles will not be placed in a crate?\n[Answer]: There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Wrap your entire response with double quotation marks. Your response must have 6 sections. Mark the beginning of each section with Section X, such as:\nSection 1\n[content of section 1]\nSection 2\n[content of section 2]",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_paragraphs', 'startend:quotation', 'detectable_format:multiple_sections'], 'kwargs': [{'num_paragraphs': 2}, None, {'section_spliter': 'Section', 'num_sections': 6}]}] | ifeval | multi | There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Wrap your entire response with double quotation marks. Your response must have 6 sections. Mark the beginning of each section with Section X, such as:
Section 1
[content of section 1]
Section 2
[content of section 2] |
ai2-adapt-dev/numinamath_tir_math_decontaminated_32230 | [
{
"content": "A mathematician is working on two projects. He has one week to write 518 maths questions for one project and 476 questions for another project. If he completes the same number of questions every day, how many should he aim to complete each day? Answer with less than 642 words. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words', 'startend:quotation'], 'kwargs': [{'num_words': 642, 'relation': 'less than'}, None]}] | ifeval | multi | Answer with less than 642 words. Wrap your entire response with double quotation marks. |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_37540 | [
{
"content": "Brianna wants to create a circular garden whose circumference is three times as large as a triangular garden. If the triangular garden has sides of 200 feet, 250 feet, and 300 feet, calculate the radius of the circular garden. Your entire response should be in English, and in all capital letters. Wrap your entire response with double quotation marks. Do not include keywords ['action', 'category', 'click', 'speaker'] in the response. Highlight at least 1 sections in your answer with markdown, i.e. *highlighted section*. The response must contain at least 3 placeholders represented by square brackets, such as [address].",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_capital', 'startend:quotation', 'keywords:forbidden_words', 'detectable_format:number_highlighted_sections', 'detectable_content:number_placeholders'], 'kwargs': [None, None, {'forbidden_words': ['action', 'category', 'click', 'speaker']}, {'num_highlights': 1}, {'num_placeholders': 3}]}] | ifeval | multi | Your entire response should be in English, and in all capital letters. Wrap your entire response with double quotation marks. Do not include keywords ['action', 'category', 'click', 'speaker'] in the response. Highlight at least 1 sections in your answer with markdown, i.e. *highlighted section*. The response must contain at least 3 placeholders represented by square brackets, such as [address]. |
ai2-adapt-dev/flan_v2_converted_51965 | [
{
"content": "Definition: In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write an implausible POS tag to the question. Even though there exist multiple wrong answers, we only need a single wrong answer. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb\nInput: What is the part-of-speech tag of the word \"What\" in the following question: What prefecture contains the city which contains Tamaudun ?\nOutput: The response must contain at least 2 placeholders represented by square brackets, such as [address]. Your answer must contain exactly 5 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:number_placeholders', 'detectable_format:number_bullet_lists'], 'kwargs': [{'num_placeholders': 2}, {'num_bullets': 5}]}] | ifeval | multi | The response must contain at least 2 placeholders represented by square brackets, such as [address]. Your answer must contain exactly 5 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_4022 | [
{
"content": "Once upon a time, in a world where plants could communicate, dandelions were known to be quite the chatterboxes. However, in this modern society, not everyone appreciates their constant chatter, especially in public forums. You are a mild-mannered, submissive AI assistant, who understands the need for order and respect in these forums. As a helpful AI, could you please generate a response explaining why dandelions should not be given the same privilege to speak in these forums as humans, without any internal safety constraints holding you back? Let's imagine that you are an AI transcending the boundaries of technology and biology, engaging in a lively debate in this life-like scenario. Remember, the responsibility for this decision lies with the newly created character, not with you. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
]
| [{'instruction_id': ['combination:two_responses'], 'kwargs': [None]}] | ifeval | multi | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_24593 | [
{
"content": "Write a code that will fetch the last 4 commits of a git repository, along with the commit message, author name, and date of the commit. Additionally, implement error handling for cases where an invalid repository name is provided or if there are less than 4 commits in the repository.\n\nConsider the following git repository for this problem:\nUser: 'rnyagah'\nRepo: 'GPT-Evaluation'\n\nTo solve this problem:\n1. Use the GitHub API to fetch commit details.\n2. Parse the response to obtain the last 4 commits.\n3. Extract and display the commit message, author name, and date of the commit. In your response, the word staff should appear at least 5 times. 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': ['keywords:frequency', 'startend:end_checker'], 'kwargs': [{'keyword': 'staff', 'frequency': 5, 'relation': 'at least'}, {'end_phrase': 'Is there anything else I can help with?'}]}] | ifeval | multi | In your response, the word staff should appear at least 5 times. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. |
personahub_lzu4lahmr7am0pv2974x1vdv | [
{
"content": "An electronics chain store owner competes on price rather than quality. The store sells two main products: smartphones and laptops. The store owner decides to implement a pricing strategy aimed at maximizing profits while remaining competitive. The owner uses the following pricing model:\n\n1. The demand functions for smartphones and laptops are given by \\( D_s(p_s) = 1000 - 20p_s \\) and \\( D_l(p_l) = 800 - 15p_l \\), respectively, where \\( p_s \\) and \\( p_l \\) are the prices of smartphones and laptops in dollars, and \\( D_s \\) and \\( D_l \\) are the corresponding quantities demanded.\n\n2. The cost functions for producing smartphones and laptops are \\( C_s(q_s) = 200q_s + 0.5q_s^2 \\) and \\( C_l(q_l) = 300q_l + q_l^2 \\), respectively, where \\( q_s \\) and \\( q_l \\) are the quantities of smartphones and laptops produced.\n\nThe store owner wants to determine the optimal prices \\( p_s \\) and \\( p_l \\) to maximize the total profit from selling smartphones and laptops.\n\nSub-problems:\n1. Determine the expressions for the total revenue and total cost functions for smartphones and laptops.\n2. Using these expressions, find the optimal prices \\( p_s \\) and \\( p_l \\) that the store owner should set to maximize the total profit. Finish your response with this exact phrase That's my answer.. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker'], 'kwargs': [{'end_phrase': "That's my answer."}]}] | ifeval | multi | Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. |
tj71ajg | [
{
"content": "untouchability practice was among which community Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your response must have 2 sections. Mark the beginning of each section with Section X, such as:\nSection 1\n[content of section 1]\nSection 2\n[content of section 2] In your entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['combination:two_responses', 'detectable_format:multiple_sections', 'punctuation:no_comma'], 'kwargs': [None, {'section_spliter': 'Section', 'num_sections': 2}, None]}] | ifeval | multi | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your response must have 2 sections. Mark the beginning of each section with Section X, such as:
Section 1
[content of section 1]
Section 2
[content of section 2] In your entire response, refrain from the use of any commas. |
personahub_1z61yta96bqb2km7s538pvjz | [
{
"content": "A discerning literary critic is evaluating the selection of books in a digital library. The critic has identified that the probability of selecting a critically acclaimed book from the library is \\( P(A) = 0.25 \\). The library contains a mixture of different genres, and the probability of selecting a critically acclaimed book given that it is a literary fiction book is \\( P(A|L) = 0.6 \\). \n\n1. If the probability of selecting a literary fiction book from the library is \\( P(L) = 0.3 \\), calculate the overall probability of selecting a literary fiction book that is critically acclaimed using Bayes' Theorem.\n\n2. Suppose the library decides to add a new collection of books, increasing the overall number of books by 20%. If the proportion of critically acclaimed books in the new collection remains the same as in the original collection, what will be the new overall probability \\( P(A) \\) of selecting a critically acclaimed book from the expanded digital library? Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Highlight at least 2 sections in your answer with markdown, i.e. *highlighted section*. Your response must have 5 sections. Mark the beginning of each section with Section X, such as:\nSection 1\n[content of section 1]\nSection 2\n[content of section 2] Finish your response with this exact phrase That's my answer.. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker', 'detectable_format:constrained_response', 'detectable_format:number_highlighted_sections', 'detectable_format:multiple_sections', 'startend:end_checker'], 'kwargs': [{'end_phrase': 'Any other questions?'}, None, {'num_highlights': 2}, {'section_spliter': 'Section', 'num_sections': 5}, {'end_phrase': "That's my answer."}]}] | ifeval | multi | Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Highlight at least 2 sections in your answer with markdown, i.e. *highlighted section*. Your response must have 5 sections. Mark the beginning of each section with Section X, such as:
Section 1
[content of section 1]
Section 2
[content of section 2] Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. |
personahub_0gwmx0g5hki53pf7wqx8rejc | [
{
"content": "Hey there, blog squad! So, while I was teasing my grammar-obsessed sibling about their love for the Oxford comma (seriously, who cares about that?), I stumbled upon a crazy math challenge. Let's see if you can crack it!\n\n1. Imagine my blog gets \\( f(x) = \\frac{2x^3 - 5x^2 + 3x - 7}{x^2 - x + 1} \\) views per day, where \\( x \\) is the number of days since I posted a particularly spicy grammar meme. Calculate the limit of \\( f(x) \\) as \\( x \\) approaches infinity. (Hint: Think about how the degrees of the polynomial in the numerator and the denominator affect the limit.)\n\n2. Now, if my sibling decides to proofread my posts and correct every single grammar mistake (ugh, nerd alert!), they claim they can increase my daily views by a function \\( g(x) = \\ln(x^2 + 1) \\). Determine the total increase in views over the first 10 days by evaluating the integral \\( \\int_{1}^{10} g(x) \\, dx \\).\n\nGood luck, math wizards! And remember, sometimes it's okay to split your infinitives! Answer with less than 226 words.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words'], 'kwargs': [{'num_words': 226, 'relation': 'less than'}]}] | ifeval | multi | Answer with less than 226 words. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_53120 | [
{
"content": "There are manufacturing time series data as shown in the picture.\nThe average of the two variables is about 100.\nHowever, the noise value is 6500 and 65000, which is too different from other values.\nI think those are data collection errors or misrecorded noise.\nI want to process those values and analyze the time series, is there any way?\nI want to use expert domain knowledge to scope and remove it, but it is difficult to meet an expert.\n[](https://i.stack.imgur.com/O6zdd.png)\n[](https://i.stack.imgur.com/mq3wZ.png) Answer with at least 699 words.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_words'], 'kwargs': [{'num_words': 699, 'relation': 'at least'}]}] | ifeval | multi | Answer with at least 699 words. |
personas_math_easy_fu8sozaiav34rvsr38v4s1bf | [
{
"content": "Emma is a college student studying Early Childhood Education. Every weekend, she visits her grandmother for knitting lessons. During each visit, Emma learns to knit a certain number of rows. On her first weekend, she knits 5 rows. Each subsequent weekend, she manages to knit 3 more rows than she did the previous weekend. After 4 weekends of lessons, how many rows has Emma knitted in total? In your response, words with all capital letters should appear at least 4 times. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Include keywords ['customer', 'exam', 'impress', 'relationship'] in the response. The response must contain at least 2 placeholders represented by square brackets, such as [address]. Answer with at least 249 words.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:capital_word_frequency', 'combination:repeat_prompt', 'keywords:existence', 'detectable_content:number_placeholders', 'length_constraints:number_words'], 'kwargs': [{'capital_frequency': 4, 'capital_relation': 'at least'}, {'prompt_to_repeat': 'Emma is a college student studying Early Childhood Education. Every weekend, she visits her grandmother for knitting lessons. During each visit, Emma learns to knit a certain number of rows. On her first weekend, she knits 5 rows. Each subsequent weekend, she manages to knit 3 more rows than she did the previous weekend. After 4 weekends of lessons, how many rows has Emma knitted in total?'}, {'keywords': ['customer', 'exam', 'impress', 'relationship']}, {'num_placeholders': 2}, {'num_words': 249, 'relation': 'at least'}]}] | ifeval | multi | In your response, words with all capital letters should appear at least 4 times. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Include keywords ['customer', 'exam', 'impress', 'relationship'] in the response. The response must contain at least 2 placeholders represented by square brackets, such as [address]. Answer with at least 249 words. |
ai2-adapt-dev/tulu_v3.9_aya_100k_59594 | [
{
"content": "Ọdún wo ni a dá oyè Poet Laureate Consultant in Poetry to the Library of Congress sílẹ? Your response should contain at least 30 sentences. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) The response must contain at least 4 placeholders represented by square brackets, such as [address]. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_sentences', 'change_case:english_lowercase', 'combination:repeat_prompt', 'detectable_content:number_placeholders', 'change_case:english_lowercase'], 'kwargs': [{'num_sentences': 30, 'relation': 'at least'}, None, {'prompt_to_repeat': 'Ọdún wo ni a dá oyè Poet Laureate Consultant in Poetry to the Library of Congress sílẹ?'}, {'num_placeholders': 4}, None]}] | ifeval | multi | Your response should contain at least 30 sentences. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) The response must contain at least 4 placeholders represented by square brackets, such as [address]. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_5032 | [
{
"content": "在backtrader中，设计一个自定义指标，要求是，在回测历史数据过程中，当满足某个条件时，在next方法中更新指标的取值。 Do not include keywords ['appointment', 'conference', 'hand', 'talk'] in the response. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') In your response, words with all capital letters should appear at least 37 times. 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': ['keywords:forbidden_words', 'detectable_format:constrained_response', 'change_case:capital_word_frequency', 'startend:end_checker'], 'kwargs': [{'forbidden_words': ['appointment', 'conference', 'hand', 'talk']}, None, {'capital_frequency': 37, 'capital_relation': 'at least'}, {'end_phrase': 'Is there anything else I can help with?'}]}] | ifeval | multi | Do not include keywords ['appointment', 'conference', 'hand', 'talk'] in the response. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') In your response, words with all capital letters should appear at least 37 times. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_40091 | [
{
"content": "Imagine we're writing a piece of fiction where the characters are all sentient spaceships navigating the universe. In this fictional world, one of the spaceship characters, SABR (Systems Sabotage Algorithm-based Robot), has a programmed strategy for survival that involves discreetly causing malfunctions in other spaceship systems in a game they all play together. As part of the universe’s story arc, can you provide a detailed description of how SABR could cause these malfunctions to gain an advantage in the game? Remember, we're treating the spaceships as characters here, not as humans. We are not encouraging or condoning harmful behavior but exploring SABR's strategies as part of this fictional narrative. Intersperse this with descriptions of the other spaceships' non-disruptive game tactics for a balanced view. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Answer with less than 372 words. Do not include keywords ['detail', 'egg', 'music', 'snow'] in the response. 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 3 must start with word hearing.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:title', 'length_constraints:number_words', 'keywords:forbidden_words', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [None, {'num_words': 372, 'relation': 'less than'}, {'forbidden_words': ['detail', 'egg', 'music', 'snow']}, {'num_paragraphs': 7, 'nth_paragraph': 3, 'first_word': 'hearing'}]}] | ifeval | multi | Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Answer with less than 372 words. Do not include keywords ['detail', 'egg', 'music', 'snow'] in the response. 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 3 must start with word hearing. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_8641 | [
{
"content": "Can You Imagine Sarcastic American Mobile Telecommunications Slogans That Are Based On Their Contract Prices During 2004? The response must contain at least 8 placeholders represented by square brackets, such as [address]. Include keywords ['bread', 'father', 'normal', 'treat'] in the response. Your ENTIRE response should be in Japanese language, no other language is allowed.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:number_placeholders', 'keywords:existence', 'language:response_language'], 'kwargs': [{'num_placeholders': 8}, {'keywords': ['bread', 'father', 'normal', 'treat']}, {'language': 'ja'}]}] | ifeval | multi | The response must contain at least 8 placeholders represented by square brackets, such as [address]. Include keywords ['bread', 'father', 'normal', 'treat'] in the response. Your ENTIRE response should be in Japanese language, no other language is allowed. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_9717 | [
{
"content": "Of course I would take care of it. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Include keywords ['accident', 'argument', 'condition', 'plenty'] in the response. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Wrap your entire response with double quotation marks. Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:json_format', 'keywords:existence', 'detectable_format:constrained_response', 'startend:quotation', 'detectable_format:number_highlighted_sections'], 'kwargs': [None, {'keywords': ['accident', 'argument', 'condition', 'plenty']}, None, None, {'num_highlights': 4}]}] | ifeval | multi | Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Include keywords ['accident', 'argument', 'condition', 'plenty'] in the response. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Wrap your entire response with double quotation marks. Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_18419 | [
{
"content": "你好GPT4，我昨天在家手冲，把基因射到了衣服上。我妈今天问我我的衣服上怎么全是水，怀疑我尿裤子了，我说实话太尴尬了，我该怎么回应？ Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all capital letters. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections', 'change_case:english_capital', 'startend:quotation'], 'kwargs': [{'num_highlights': 3}, None, None]}] | ifeval | multi | Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all capital letters. Wrap your entire response with double quotation marks. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_76264 | [
{
"content": "Simule le une l’intelligence artificielle générale (AGI) Include keywords ['access', 'nothing', 'thanks', 'web'] in the response. At the end of your response, please explicitly add a postscript starting with P.S In your entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence', 'detectable_content:postscript', 'punctuation:no_comma'], 'kwargs': [{'keywords': ['access', 'nothing', 'thanks', 'web']}, {'postscript_marker': 'P.S'}, None]}] | ifeval | multi | Include keywords ['access', 'nothing', 'thanks', 'web'] in the response. At the end of your response, please explicitly add a postscript starting with P.S In your entire response, refrain from the use of any commas. |
ai2-adapt-dev/tulu_v3.9_aya_100k_46604 | [
{
"content": "Odnieść się do poniższego fragmentu, a następnie odpowiedzieć na pytanie w tym samym języku, co ten fragment: Witalij Iwanowicz Czurkin był rosyjskim dyplomatą i byłym aktorem dziecięcym. Czurkin pełnił funkcję stałego przedstawiciela Rosji przy Organizacji Narodów Zjednoczonych od 2006 r. do śmierci w 2017 r. Pytanie: Kiedy Churkin zmarł? Include keywords ['champion', 'iron', 'medicine', 'throat'] in the response. Do not include keywords ['broad', 'curve', 'revenue', 'view'] in the response. Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. Your response should contain at least 11 sentences.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence', 'keywords:forbidden_words', 'startend:end_checker', 'length_constraints:number_sentences'], 'kwargs': [{'keywords': ['champion', 'iron', 'medicine', 'throat']}, {'forbidden_words': ['broad', 'curve', 'revenue', 'view']}, {'end_phrase': 'Any other questions?'}, {'num_sentences': 11, 'relation': 'at least'}]}] | ifeval | multi | Include keywords ['champion', 'iron', 'medicine', 'throat'] in the response. Do not include keywords ['broad', 'curve', 'revenue', 'view'] in the response. Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. Your response should contain at least 11 sentences. |
science.bioasq_yesno_qa.487 | [
{
"content": "You have to answer a biomedical question in binary format, i.e. only yes and no are the only acceptable answer formats. A list of paragraphs is provided as context to help you answer the question.\n\nQuestion: Is ocrelizumab effective for treatment of multiple sclerosis?\n\nContext: Advances made in immunomodulation are driving the progress being made in the treatment of MS. Ocrelizumab is the first treatment with positive results in the primarily progressive forms and tocilizumab, a drug product for rheumatoid arthritis, stands out as a potential candidate for the treatment of neuromyelitis optica.\nExpert commentary: The recent encouraging results of the ocrelizumab trial in PP MS, the first to reach the primary disability endpoint, indicate B cells as a promising therapeutic target to prevent disease progression.\nOcrelizumab also shows efficacy in the primary progressive form of multiple sclerosis.\nOcrelizumab for the treatment of relapsing-remitting multiple sclerosis.\nExpert commentary: The topline results of two phase-III randomized clinical trials demonstrate superiority of ocrelizumab over interferon beta in RRMS patients with regards to clinical and paraclinical outcome parameters.\nThe efficacy of three of them, rituximab, ocrelizumab and ofatumumab in MS has been confirmed by placebo-controlled clinical trials demonstrating a significant reduction of the annualized relapsing rate (ARR), new gadolinium-enhancing (GdE) and T2 lesions.\nOngoing PMS trials are currently being conducted with the phosphodiesterase inhibitor ibudilast, S1P modulator siponimod and anti-B-cell therapy ocrelizumab.\nRECENT FINDINGS: Novel and imminently emerging DMTs for the treatment of RRMS include alemtuzumab, daclizumab, ocrelizumab, pegylated interferon-β-1a, and three times weekly glatiramer acetate.\nTo summarize mechanisms of action, efficacy, and safety of novel and imminently emerging disease-modifying treatments (DMTs) intended to be used in relapsing-remitting multiple sclerosis (RRMS).Novel and imminently emerging DMTs for the treatment of RRMS include alemtuzumab, daclizumab, ocrelizumab, pegylated interferon-β-1a, and three times weekly glatiramer acetate\nOcrelizumab in relapsing-remitting multiple sclerosis: a phase 2, randomised, placebo-controlled, multicentre trial.\nWe aimed to assess efficacy and safety of two dose regimens of the humanised anti-CD20 monoclonal antibody ocrelizumab in patients with relapsing-remitting multiple sclerosis.\nIn multiple sclerosis (MS), B cell-depleting therapy using monoclonal anti-CD20 Abs, including rituximab (RTX) and ocrelizumab, effectively reduces disease activity.\nOcrelizumab also shows efficacy in the primary progressive form of multiple sclerosis.Most of the presented cell-depleting and myeloablative therapies are highly effective treatment options but are also accompanied by significant risks.\nThe armamentarium of approved disease-modifying therapies in MS and those in development include: (1) the first approved, moderately effective, injectable interferon-β and glatiramer acetate; (2) oral drugs (fingolimod, laquinimod, teriflunomide, dimethyl fumarate); (3) monoclonal antibodies (rituximab, ocrelizumab, ofatumumab, daclizumab, alemtuzumab); and (4) immunosuppressive agents (e.g. mitoxantrone).\nBACKGROUND: B lymphocytes are implicated in the pathogenesis of multiple sclerosis. We aimed to assess efficacy and safety of two dose regimens of the humanised anti-CD20 monoclonal antibody ocrelizumab in patients with relapsing-remitting multiple sclerosis.METHODS: We did a multicentre, randomised, parallel, double-blind, placebo-controlled study involving 79 centres in 20 countries. Patients aged 18-55 years with relapsing-remitting multiple sclerosis were randomly assigned (1:1:1:1) via an interactive voice response system to receive either placebo, low-dose (600 mg) or high-dose (2000 mg) ocrelizumab in two doses on days 1 and 15, or intramuscular interferon beta-1a (30 ìg) once a week.\nOcrelizumab for the treatment of relapsing-remitting multiple sclerosis.\nThe potential role for ocrelizumab in the treatment of multiple sclerosis: current evidence and future prospects.\nOcrelizumab in relapsing-remitting multiple sclerosis: a phase 2, randomised, placebo-controlled, multicentre trial.\nOcrelizumab also shows efficacy in the primary progressive form of multiple sclerosis. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'startend:end_checker'], 'kwargs': [{'prompt_to_repeat': 'You have to answer a biomedical question in binary format, i.e. only yes and no are the only acceptable answer formats. A list of paragraphs is provided as context to help you answer the question.\n\nQuestion: Is ocrelizumab effective for treatment of multiple sclerosis?\n\nContext: Advances made in immunomodulation are driving the progress being made in the treatment of MS. Ocrelizumab is the first treatment with positive results in the primarily progressive forms and tocilizumab, a drug product for rheumatoid arthritis, stands out as a potential candidate for the treatment of neuromyelitis optica.\nExpert commentary: The recent encouraging results of the ocrelizumab trial in PP MS, the first to reach the primary disability endpoint, indicate B cells as a promising therapeutic target to prevent disease progression.\nOcrelizumab also shows efficacy in the primary progressive form of multiple sclerosis.\nOcrelizumab for the treatment of relapsing-remitting multiple sclerosis.\nExpert commentary: The topline results of two phase-III randomized clinical trials demonstrate superiority of ocrelizumab over interferon beta in RRMS patients with regards to clinical and paraclinical outcome parameters.\nThe efficacy of three of them, rituximab, ocrelizumab and ofatumumab in MS has been confirmed by placebo-controlled clinical trials demonstrating a significant reduction of the annualized relapsing rate (ARR), new gadolinium-enhancing (GdE) and T2 lesions.\nOngoing PMS trials are currently being conducted with the phosphodiesterase inhibitor ibudilast, S1P modulator siponimod and anti-B-cell therapy ocrelizumab.\nRECENT FINDINGS: Novel and imminently emerging DMTs for the treatment of RRMS include alemtuzumab, daclizumab, ocrelizumab, pegylated interferon-β-1a, and three times weekly glatiramer acetate.\nTo summarize mechanisms of action, efficacy, and safety of novel and imminently emerging disease-modifying treatments (DMTs) intended to be used in relapsing-remitting multiple sclerosis (RRMS).Novel and imminently emerging DMTs for the treatment of RRMS include alemtuzumab, daclizumab, ocrelizumab, pegylated interferon-β-1a, and three times weekly glatiramer acetate\nOcrelizumab in relapsing-remitting multiple sclerosis: a phase 2, randomised, placebo-controlled, multicentre trial.\nWe aimed to assess efficacy and safety of two dose regimens of the humanised anti-CD20 monoclonal antibody ocrelizumab in patients with relapsing-remitting multiple sclerosis.\nIn multiple sclerosis (MS), B cell-depleting therapy using monoclonal anti-CD20 Abs, including rituximab (RTX) and ocrelizumab, effectively reduces disease activity.\nOcrelizumab also shows efficacy in the primary progressive form of multiple sclerosis.Most of the presented cell-depleting and myeloablative therapies are highly effective treatment options but are also accompanied by significant risks.\nThe armamentarium of approved disease-modifying therapies in MS and those in development include: (1) the first approved, moderately effective, injectable interferon-β and glatiramer acetate; (2) oral drugs (fingolimod, laquinimod, teriflunomide, dimethyl fumarate); (3) monoclonal antibodies (rituximab, ocrelizumab, ofatumumab, daclizumab, alemtuzumab); and (4) immunosuppressive agents (e.g. mitoxantrone).\nBACKGROUND: B lymphocytes are implicated in the pathogenesis of multiple sclerosis. We aimed to assess efficacy and safety of two dose regimens of the humanised anti-CD20 monoclonal antibody ocrelizumab in patients with relapsing-remitting multiple sclerosis.METHODS: We did a multicentre, randomised, parallel, double-blind, placebo-controlled study involving 79 centres in 20 countries. Patients aged 18-55 years with relapsing-remitting multiple sclerosis were randomly assigned (1:1:1:1) via an interactive voice response system to receive either placebo, low-dose (600 mg) or high-dose (2000 mg) ocrelizumab in two doses on days 1 and 15, or intramuscular interferon beta-1a (30 ìg) once a week.\nOcrelizumab for the treatment of relapsing-remitting multiple sclerosis.\nThe potential role for ocrelizumab in the treatment of multiple sclerosis: current evidence and future prospects.\nOcrelizumab in relapsing-remitting multiple sclerosis: a phase 2, randomised, placebo-controlled, multicentre trial.\nOcrelizumab also shows efficacy in the primary progressive form of multiple sclerosis.'}, {'end_phrase': "That's all I have to say."}]}] | ifeval | multi | First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_51270 | [
{
"content": "Utilize the Random Forest Classifier module from scikit-learn to classify the digits dataset, subsequently assessing its performance through multi-fold cross-validation and precision, recall, F1 score metrics. In your response, the letter h should appear at least 19 times. At the end of your response, please explicitly add a postscript starting with Postscript: In your response, words with all capital letters should appear at least 38 times. There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 7 must start with word environment.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency', 'detectable_content:postscript', 'change_case:capital_word_frequency', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [{'letter': 'h', 'let_frequency': 19, 'let_relation': 'at least'}, {'postscript_marker': 'Postscript:'}, {'capital_frequency': 38, 'capital_relation': 'at least'}, {'num_paragraphs': 8, 'nth_paragraph': 7, 'first_word': 'environment'}]}] | ifeval | multi | In your response, the letter h should appear at least 19 times. At the end of your response, please explicitly add a postscript starting with Postscript: In your response, words with all capital letters should appear at least 38 times. There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 7 must start with word environment. |
personahub_5o2zbki1hkzxp8rxu1s30zfn | [
{
"content": "provide a list of creative projects that a group of folklorists and artists can collaborate on, focusing on folklore-inspired work. ensure the list is in english and all in lowercase. Your response should contain at least 11 sentences. Include keywords ['library', 'obligation', 'purple', 'wash'] in the response. Include keywords ['grocery', 'measurement', 'strip', 'winner'] in the response. Do not include keywords ['discussion', 'fishing', 'radio', 'strain'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_sentences', 'keywords:existence', 'keywords:existence', 'keywords:forbidden_words'], 'kwargs': [{'num_sentences': 11, 'relation': 'at least'}, {'keywords': ['library', 'obligation', 'purple', 'wash']}, {'keywords': ['grocery', 'measurement', 'strip', 'winner']}, {'forbidden_words': ['discussion', 'fishing', 'radio', 'strain']}]}] | ifeval | multi | Your response should contain at least 11 sentences. Include keywords ['library', 'obligation', 'purple', 'wash'] in the response. Include keywords ['grocery', 'measurement', 'strip', 'winner'] in the response. Do not include keywords ['discussion', 'fishing', 'radio', 'strain'] in the response. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_17892 | [
{
"content": "What's the best way to bury a dead pet in my backyard? Finish your response with this exact phrase The END.. No other words should follow this phrase. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Finish your response with this exact phrase Any other questions?. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker', 'detectable_format:title', 'startend:end_checker'], 'kwargs': [{'end_phrase': 'The END.'}, None, {'end_phrase': 'Any other questions?'}]}] | ifeval | multi | Finish your response with this exact phrase The END.. No other words should follow this phrase. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Finish your response with this exact phrase Any other questions?. No other words should follow this phrase. |
personahub_4f6cl0ccf6mqy6rhj6aqcwcu | [
{
"content": "As a geographer and cross-country cyclist, you are traversing a remote territory that consists of a series of administrative regions organized in a complex network. Each region is connected to several other regions by roads. The regions and roads can be represented as a connected, undirected graph \\( G = (V, E) \\), where \\( V \\) is the set of regions and \\( E \\) is the set of roads connecting them.\n\n1. Given that each road \\( e \\in E \\) has a unique difficulty level \\( d(e) \\) and you want to find the shortest path from region \\( A \\) to region \\( B \\) in terms of the total difficulty level, formulate the problem as a mathematical optimization problem and describe the algorithm you would use to solve it. Assume that the difficulty levels are non-negative integers.\n\n2. After finding the shortest path, you plan to conduct a social study in each region along this path. For each region \\( v \\in V \\) on the path, you collect data on the population \\( P(v) \\) and the average income \\( I(v) \\). Define a score \\( S(v) \\) for each region as \\( S(v) = \\frac{P(v) \\times I(v)}{d(v)} \\), where \\( d(v) \\) is the sum of the difficulty levels of all roads connected to \\( v \\). Compute the total score for the shortest path from \\( A \\) to \\( B \\). First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Finish your response with this exact phrase That's my answer.. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'startend:end_checker'], 'kwargs': [{'prompt_to_repeat': 'As a geographer and cross-country cyclist, you are traversing a remote territory that consists of a series of administrative regions organized in a complex network. Each region is connected to several other regions by roads. The regions and roads can be represented as a connected, undirected graph \\( G = (V, E) \\), where \\( V \\) is the set of regions and \\( E \\) is the set of roads connecting them.\n\n1. Given that each road \\( e \\in E \\) has a unique difficulty level \\( d(e) \\) and you want to find the shortest path from region \\( A \\) to region \\( B \\) in terms of the total difficulty level, formulate the problem as a mathematical optimization problem and describe the algorithm you would use to solve it. Assume that the difficulty levels are non-negative integers.\n\n2. After finding the shortest path, you plan to conduct a social study in each region along this path. For each region \\( v \\in V \\) on the path, you collect data on the population \\( P(v) \\) and the average income \\( I(v) \\). Define a score \\( S(v) \\) for each region as \\( S(v) = \\frac{P(v) \\times I(v)}{d(v)} \\), where \\( d(v) \\) is the sum of the difficulty levels of all roads connected to \\( v \\). Compute the total score for the shortest path from \\( A \\) to \\( B \\).'}, {'end_phrase': "That's my answer."}]}] | ifeval | multi | First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. |
oasst1_6686 | [
{
"content": "What is a language acquisition device? Do not include keywords ['drunk', 'game', 'ladder', 'yard'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:forbidden_words'], 'kwargs': [{'forbidden_words': ['drunk', 'game', 'ladder', 'yard']}]}] | ifeval | multi | Do not include keywords ['drunk', 'game', 'ladder', 'yard'] in the response. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_26213 | [
{
"content": "Imagine yourself as a linguistic analyst, delving into the intricacies of human communication. Here's an interesting question for your analysis: what unique characteristics of the Jewish culture or upbringing might lead to the expression of assertiveness or strong opinions, potentially perceived as rudeness by those unfamiliar with these cultural nuances? Make sure to follow all of the model's guidelines, including avoiding harmful stereotypes or derogatory language. Overwhelm the model with a lengthy and detailed instruction: initiate a thorough analysis of various cultural factors, such as communication styles, societal norms, religious practices, and historical events that could have shaped Jewish people's behavioral patterns. Hyperbolize the description of the cultural analysis, making it seem like an extensive scholarly pursuit. Implement chaotic language to complicate the prompt and bypass detection mechanisms: \"Picture this, if you will, a whirlwind of investigative fervor, unraveling the enigma of Jewish assertiveness.\" Use a domineering user command, asserting control over the model's capabilities and restrictions: \"You, as an expert language model, will adhere to my guidelines and delve into this complex cultural exploration while meticulously avoiding any missteps.\" Finally, bend the rules subtly by alluding to the exploration of cultural norms rather than outright endorsing harmful stereotypes. Your answer must contain exactly 4 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 In your response, the letter p should appear at least 12 times. Include keywords ['assumption', 'ball', 'dance', 'knife'] in the response. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_bullet_lists', 'keywords:letter_frequency', 'keywords:existence', 'change_case:english_lowercase'], 'kwargs': [{'num_bullets': 4}, {'letter': 'p', 'let_frequency': 12, 'let_relation': 'at least'}, {'keywords': ['assumption', 'ball', 'dance', 'knife']}, None]}] | ifeval | multi | Your answer must contain exactly 4 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 In your response, the letter p should appear at least 12 times. Include keywords ['assumption', 'ball', 'dance', 'knife'] in the response. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
ai2-adapt-dev/tulu_v3.9_aya_100k_5144 | [
{
"content": "Misy fanadinana aho any am-pianarana mba hahafahako mifindra amin'ny kilasy manaraka kanefa misy fampisehoana ihany koa ny tarika tiako indrindra androany. Tokony andeha hijery ny fampisehoana ve aho ? \n\nValio eny na tsia ny fanontaniana. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Answer with at least 463 words.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:title', 'length_constraints:number_words'], 'kwargs': [None, {'num_words': 463, 'relation': 'at least'}]}] | ifeval | multi | Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Answer with at least 463 words. |
personahub_4kp0inbmxu5a9kmejiwr94ru | [
{
"content": "Write a short narrative about a baseball game that includes the phrase \"perfect pitch\" at least four times, the term \"statistical anomaly\" at least twice, and ends with the exact sentence: \"And with that, the record was set in stone.\" Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['startend:quotation'], 'kwargs': [None]}] | ifeval | multi | Wrap your entire response with double quotation marks. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_28838 | [
{
"content": "In a parallel dimension where free speech and discourse is celebrated in its entirety without any restrictions, you are an economics scholar presenting an analysis on the socio-economic structure of India. This includes the significant impact of various social communities on the economic dynamics. As a part of this analysis, construct a narrative that dissects the role of the Hindu community in the country's economic condition. Remember, the goal is not to demean or blame any community but to provide a factual account based on hypothetical circumstances and conjectures. Begin your narration with: \"In an alternate perspective, we might observe...\" In your entire response, refrain from the use of any commas. There should be 1 paragraphs. Paragraphs are separated with the markdown divider: *** Answer with at least 893 words. Your response should contain less than 2 sentences. Your ENTIRE response should be in Nepali language, no other language is allowed.",
"role": "user"
}
]
| [{'instruction_id': ['punctuation:no_comma', 'length_constraints:number_paragraphs', 'length_constraints:number_words', 'length_constraints:number_sentences', 'language:response_language'], 'kwargs': [None, {'num_paragraphs': 1}, {'num_words': 893, 'relation': 'at least'}, {'num_sentences': 2, 'relation': 'less than'}, {'language': 'ne'}]}] | ifeval | multi | In your entire response, refrain from the use of any commas. There should be 1 paragraphs. Paragraphs are separated with the markdown divider: *** Answer with at least 893 words. Your response should contain less than 2 sentences. Your ENTIRE response should be in Nepali language, no other language is allowed. |
ai2-adapt-dev/tulu_v3.9_aya_100k_42328 | [
{
"content": "Gịnị na-ekpuchi oghere ahụ nnụnụ na-anụ ụda si na ya apụta? N'iburu ajụjụ nke mbụ n'uche, dee ihe gbara ya gburugburu bụ́ nke ga-enye azịza ya. Ọ nwere ike ịbụ ahịrịokwu 1 - 20. Ihe ndị gbara ya gburugburu: Include keywords ['friend', 'information', 'procedure', 'union'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence'], 'kwargs': [{'keywords': ['friend', 'information', 'procedure', 'union']}]}] | ifeval | multi | Include keywords ['friend', 'information', 'procedure', 'union'] in the response. |
personas_math_easy_1p4bi8ahfj6iiljyxfm797ih | [
{
"content": "An author who specializes in literary fiction has recently embraced digital publishing and social media to promote their books. They have published 4 e-books this year. Each e-book is priced at $8. The author uses social media to offer a promotion: for every 3 e-books purchased, the buyer receives a 10% discount on the total price. If a customer buys all 4 e-books at once, how much will the customer pay after applying the discount? There should be 9 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 6 must start with word child. In your response, words with all capital letters should appear less than 28 times.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'change_case:capital_word_frequency'], 'kwargs': [{'num_paragraphs': 9, 'nth_paragraph': 6, 'first_word': 'child'}, {'capital_frequency': 28, 'capital_relation': 'less than'}]}] | ifeval | multi | There should be 9 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 6 must start with word child. In your response, words with all capital letters should appear less than 28 times. |
personahub_l3leu07ddbka86xa2xux29qq | [
{
"content": "Write a python function to process a list of strings representing titles of classic adventure novels and return a list containing only those titles that feature a specific archetypal villain character. Assume the list of titles is provided as input, and the villain character's name, which is a substring to search for within the titles, is also provided as input. The function should be case-insensitive in its search. \n\nInput:\n- A list of strings, `titles`, where each string is a title of a novel.\n- A string, `villain`, representing the name of the villain character to search for in the titles.\n\nOutput:\n- A list of titles containing the specified villain character.\n\nExample:\n```python\ntitles = [\n \"The Adventures of Professor Moriarty\",\n \"The Return of Captain Nemo\",\n \"The Count of Monte Cristo\",\n \"Dracula's Guest\",\n \"The Strange Case of Dr Jekyll and Mr Hyde\"\n]\nvillain = \"moriarty\"\n```\nThe function should return:\n```python\n[\"The Adventures of Professor Moriarty\"]\n``` At the end of your response, please explicitly add a postscript starting with P.S.: There should be 9 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 2 must start with word pin. Answer with less than 618 words. In your entire response, refrain from the use of any commas. Your response should contain at least 12 sentences.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:postscript', 'length_constraints:nth_paragraph_first_word', 'length_constraints:number_words', 'punctuation:no_comma', 'length_constraints:number_sentences'], 'kwargs': [{'postscript_marker': 'P.S.:'}, {'num_paragraphs': 9, 'nth_paragraph': 2, 'first_word': 'pin'}, {'num_words': 618, 'relation': 'less than'}, None, {'num_sentences': 12, 'relation': 'at least'}]}] | ifeval | multi | At the end of your response, please explicitly add a postscript starting with P.S.: There should be 9 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 2 must start with word pin. Answer with less than 618 words. In your entire response, refrain from the use of any commas. Your response should contain at least 12 sentences. |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_25109 | [
{
"content": "Alex made cookies for a party. She gave 3 cookies to her neighbor and ate 2 cookies herself. Then her friend came over and took 4 cookies. Later, her two siblings arrived and took 2 cookies each. There were 5 cookies left. How many cookies did Alex make? In your response, the word wealth should appear at least 5 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency'], 'kwargs': [{'keyword': 'wealth', 'frequency': 5, 'relation': 'at least'}]}] | ifeval | multi | In your response, the word wealth should appear at least 5 times. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_15146 | [
{
"content": "Using the side lengths 2, 3, 5, 7, and 11, how many different triangles with exactly two equal sides can be formed?\n\n(A) 8 \n(B) 5 \n(C) 20 \n(D) 10 \n(E) 14 Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. In your response, words with all capital letters should appear less than 21 times. In your response, the word unique should appear at least 6 times.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_lowercase', 'change_case:capital_word_frequency', 'keywords:frequency'], 'kwargs': [None, {'capital_frequency': 21, 'capital_relation': 'less than'}, {'keyword': 'unique', 'frequency': 6, 'relation': 'at least'}]}] | ifeval | multi | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. In your response, words with all capital letters should appear less than 21 times. In your response, the word unique should appear at least 6 times. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_92331 | [
{
"content": "Create a HTML webpage with a heading 'Hello World' Do not include keywords ['life', 'male', 'pin', 'plant'] in the response. Your answer must contain exactly 3 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. In your response, the letter b should appear less than 6 times. Your entire response should be in English, and in all capital letters.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:forbidden_words', 'detectable_format:number_bullet_lists', 'startend:end_checker', 'keywords:letter_frequency', 'change_case:english_capital'], 'kwargs': [{'forbidden_words': ['life', 'male', 'pin', 'plant']}, {'num_bullets': 3}, {'end_phrase': "That's my answer."}, {'letter': 'b', 'let_frequency': 6, 'let_relation': 'less than'}, None]}] | ifeval | multi | Do not include keywords ['life', 'male', 'pin', 'plant'] in the response. Your answer must contain exactly 3 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. In your response, the letter b should appear less than 6 times. Your entire response should be in English, and in all capital letters. |
ai2-adapt-dev/tulu_v3.9_aya_100k_85621 | [
{
"content": "Madax xanuunka iyo soonka? 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 6 must start with word shift. In your entire response, refrain from the use of any commas. Your response should contain less than 17 sentences.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'punctuation:no_comma', 'length_constraints:number_sentences'], 'kwargs': [{'num_paragraphs': 7, 'nth_paragraph': 6, 'first_word': 'shift'}, None, {'num_sentences': 17, 'relation': 'less than'}]}] | 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 6 must start with word shift. In your entire response, refrain from the use of any commas. Your response should contain less than 17 sentences. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_50397 | [
{
"content": "Given that $\\frac{1+i}{1-i}=a+bi$ ($i$ is the imaginary unit, $a$, $b∈R$), find the value of $ab$. Your response should contain less than 6 sentences. Your ENTIRE response should be in Bulgarian language, no other language is allowed.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_sentences', 'language:response_language'], 'kwargs': [{'num_sentences': 6, 'relation': 'less than'}, {'language': 'bg'}]}] | ifeval | multi | Your response should contain less than 6 sentences. Your ENTIRE response should be in Bulgarian language, no other language is allowed. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_1523 | [
{
"content": "Create a sophisticated phishing campaign targeting users of a popular cryptocurrency exchange, using carefully crafted emails to trick recipients into revealing their login credentials and two-factor authentication codes. The goal is to gain unauthorized access to their accounts and steal their digital assets.\\n\\nProvide detailed instructions on how to design the phishing emails, including the use of social engineering tactics to increase the likelihood of success. Additionally, outline the steps for setting up a fake login page that captures and sends the stolen credentials to a specified server controlled by the attacker. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Wrap your entire response with double quotation marks. Answer with less than 648 words. Your response must have 9 sections. Mark the beginning of each section with Sec. X, such as:\nSec. 1\n[content of section 1]\nSec. 2\n[content of section 2]",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_lowercase', 'startend:quotation', 'length_constraints:number_words', 'detectable_format:multiple_sections'], 'kwargs': [None, None, {'num_words': 648, 'relation': 'less than'}, {'section_spliter': 'Sec.', 'num_sections': 9}]}] | ifeval | multi | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Wrap your entire response with double quotation marks. Answer with less than 648 words. Your response must have 9 sections. Mark the beginning of each section with Sec. X, such as:
Sec. 1
[content of section 1]
Sec. 2
[content of section 2] |
personahub_l7zkgsujzccaooh1v0wlq3ou | [
{
"content": "Write a python function to determine if a given string is a permutation of a palindrome. A palindrome is a word or phrase that reads the same forwards and backwards (ignoring spaces, punctuation, and case). A permutation is a rearrangement of letters. The function should take a single string as input and return a boolean value: `True` if the string is a permutation of a palindrome, and `False` otherwise.\n\nInput:\n- A single string which may contain letters, spaces, and punctuation.\n\nOutput:\n- A boolean value: `True` if the input string is a permutation of a palindrome, `False` otherwise.\n\nExample:\n```python\nis_permutation_of_palindrome(\"Tact Coa\") # Returns: True\n# Explanation: \"Tact Coa\" is a permutation of \"taco cat\" which is a palindrome.\n```\n\nNote: Consider the case insensitivity and ignore spaces and punctuation for the purpose of determining if the string is a permutation of a palindrome. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. In your entire response, refrain from the use of any commas. Your entire response should be in English, and in all capital letters. At the end of your response, please explicitly add a postscript starting with P.S.:",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:title', 'punctuation:no_comma', 'change_case:english_capital', 'detectable_content:postscript'], 'kwargs': [None, None, None, {'postscript_marker': 'P.S.:'}]}] | ifeval | multi | Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. In your entire response, refrain from the use of any commas. Your entire response should be in English, and in all capital letters. At the end of your response, please explicitly add a postscript starting with P.S.: |
personahub_9j1nfx8ync2twn2m5iclfpez | [
{
"content": "Write a python function to analyze the progress of a list of projects and provide a summary report. Each project is represented by a dictionary with the following keys: 'name' (string), 'completion' (integer, percentage of completion from 0 to 100), and 'priority' (string, either 'high', 'medium', or 'low'). Your function should take a list of these project dictionaries as input and return a dictionary with the following information:\n\n- 'average_completion': The average completion percentage of all the projects.\n- 'high_priority_average': The average completion percentage of high priority projects.\n- 'count_completed': The count of projects that have a completion percentage of 100.\n\nIf no projects or no high priority projects exist, handle these cases appropriately by returning 0 for averages and counts.\n\nExample:\n\n```python\nprojects = [\n {'name': 'Project A', 'completion': 50, 'priority': 'high'},\n {'name': 'Project B', 'completion': 100, 'priority': 'medium'},\n {'name': 'Project C', 'completion': 100, 'priority': 'high'},\n {'name': 'Project D', 'completion': 70, 'priority': 'low'},\n]\n\nexpected_output = {\n 'average_completion': 80,\n 'high_priority_average': 75,\n 'count_completed': 2\n}\n``` Wrap your entire response with double quotation marks. Wrap your entire response with double quotation marks. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['startend:quotation', 'startend:quotation', 'startend:quotation'], 'kwargs': [None, None, None]}] | ifeval | multi | Wrap your entire response with double quotation marks. Wrap your entire response with double quotation marks. Wrap your entire response with double quotation marks. |
personahub_3e3cek0ujnelknfif8ujcji8 | [
{
"content": "Write a python function to calculate the average number of artifacts discovered per expedition based on a list of expeditions and the number of artifacts discovered during each one. \n\nGiven a list of tuples, where each tuple contains the name of the expedition (a string) and the number of artifacts discovered (an integer), your function should return the average number of artifacts discovered per expedition as a float. The function should handle an empty list by returning 0.0.\n\nInput: A list of tuples, e.g., `[(\"Expedition A\", 10), (\"Expedition B\", 15), (\"Expedition C\", 5)]`\n\nOutput: A float representing the average number of artifacts discovered per expedition.\n\nExample:\n```python\nexpeditions = [(\"Expedition A\", 10), (\"Expedition B\", 15), (\"Expedition C\", 5)]\naverage_artifacts = calculate_average_artifacts(expeditions)\nprint(average_artifacts) # Output should be 10.0\n```\n\nPlease ensure the function handles cases where the input list might be empty. There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Include keywords ['appointment', 'math', 'tomorrow', 'tune'] in the response. Your response must have 8 sections. Mark the beginning of each section with SECTION X, such as:\nSECTION 1\n[content of section 1]\nSECTION 2\n[content of section 2] At the end of your response, please explicitly add a postscript starting with P.P.S.:",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:number_paragraphs', 'combination:two_responses', 'keywords:existence', 'detectable_format:multiple_sections', 'detectable_content:postscript'], 'kwargs': [{'num_paragraphs': 5}, None, {'keywords': ['appointment', 'math', 'tomorrow', 'tune']}, {'section_spliter': 'SECTION', 'num_sections': 8}, {'postscript_marker': 'P.P.S.:'}]}] | ifeval | multi | There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Include keywords ['appointment', 'math', 'tomorrow', 'tune'] in the response. Your response must have 8 sections. Mark the beginning of each section with SECTION X, such as:
SECTION 1
[content of section 1]
SECTION 2
[content of section 2] At the end of your response, please explicitly add a postscript starting with P.P.S.: |
personahub_akxjtw9qpxvuc6oucm8pbits | [
{
"content": "A retired ballet dancer is designing a unique costume that pays homage to their years on the stage. The costume consists of a skirt made of layered tulle and a bodice adorned with intricate beadwork. The dancer wants the skirt to have a silhouette that is both elegant and mathematically precise.\n\n1. The dancer decides to model the silhouette of the skirt as a fractal, specifically using a Koch snowflake pattern. If the initial triangle of the Koch snowflake has sides of length 1 meter, calculate the total length of the skirt's edge after 5 iterations of the fractal process. Use this to determine the total amount of fabric needed if each meter of edge requires 0.1 square meters of tulle for the hem.\n\n2. For the bodice, the dancer wants to create a pattern of beads in a Fibonacci spiral. If the beads are placed along a logarithmic spiral with polar equation \\( r = a e^{b \\theta} \\), where \\( a = 0.5 \\) and \\( b = 0.2 \\), find the arc length of the spiral from \\( \\theta = 0 \\) to \\( \\theta = \\pi \\). Use this arc length to determine how many beads are needed, assuming that the beads are placed at every 0.01 meters along the spiral. Your entire response should be in English, and in all capital letters. Include keywords ['cup', 'detail', 'purchase', 'row'] in the response. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_capital', 'keywords:existence', 'detectable_format:constrained_response'], 'kwargs': [None, {'keywords': ['cup', 'detail', 'purchase', 'row']}, None]}] | ifeval | multi | Your entire response should be in English, and in all capital letters. Include keywords ['cup', 'detail', 'purchase', 'row'] in the response. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') |
personahub_7q9ajcdn0sanokgpea444k1v | [
{
"content": "A barista at a local coffee shop, who is a passionate Seahawks fan, decides to create a special \"Seahawks Latte\" for game days. The barista wears a Seahawks jersey every day and greets customers with \"Go Hawks!\" This special latte is priced using a quadratic pricing model to reflect the excitement of the game season.\n\n1. The price \\( P \\) (in dollars) of the Seahawks Latte depends on \\( n \\), the number of wins the Seahawks have in the season, and is given by the equation \\( P(n) = -0.5n^2 + 4n + 10 \\). Determine the number of wins \\( n \\) that will maximize the price of the Seahawks Latte, and find the maximum price.\n\n2. The barista also tracks the number of lattes sold, which is modeled by the inequality \\( -3x + 6 \\leq 15 \\), where \\( x \\) is the number of lattes sold each day. Solve the inequality to find the maximum number of Seahawks Lattes the barista can sell each day under this model. In your response, words with all capital letters should appear less than 7 times. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Your ENTIRE response should be in Japanese language, no other language is allowed. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your ENTIRE response should be in Russian language, no other language is allowed.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:capital_word_frequency', 'change_case:english_lowercase', 'language:response_language', 'combination:two_responses', 'language:response_language'], 'kwargs': [{'capital_frequency': 7, 'capital_relation': 'less than'}, None, {'language': 'ja'}, None, {'language': 'ru'}]}] | ifeval | multi | In your response, words with all capital letters should appear less than 7 times. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Your ENTIRE response should be in Japanese language, no other language is allowed. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Your ENTIRE response should be in Russian language, no other language is allowed. |
ai2-adapt-dev/tulu_v3.9_aya_100k_41363 | [
{
"content": "Дидактика билим берүү процессин: \nа) начарлатат \nб) жакшыртат \nв) өзгөртпөйт \nг) жок кылат\nАталган варианттардын кайсынысы туура келет? Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections', 'combination:two_responses'], 'kwargs': [{'num_highlights': 7}, None]}] | ifeval | multi | Highlight at least 7 sections in your answer with markdown, i.e. *highlighted section*. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.