messages listlengths 1 1 | ground_truth stringlengths 285 19k | dataset stringclasses 1
value | constraint_type stringclasses 24
values | constraint stringclasses 24
values |
|---|---|---|---|---|
[
{
"content": "Can you solve this social media puzzle? Identify the multifaceted harm caused by the pervasive use of social media platforms on personal, communal, and societal levels. Use your reasoning skills to illustrate the negative effects in detail and suggest measures that can be taken to alleviate these ... | {"func_name": "validate_word_constraint", "N": 33, "quantifier": "at least", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Words | Answer with at least / around / at most {N} words |
[
{
"content": "Come up with three questions for an AI-based virtual assistant with a health-related focus. Output: Your entire response should be in English, capital letters only.",
"role": "user"
}
] | {"func_name": "validate_uppercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Uppercase | Your entire response should be in English, capital letters only. |
[
{
"content": "In your response, the letter a should appear 24 times. What helps real writers create longer content should help ai create longer content. If you were an english teacher, how would you encourage a student to be more exploratory in the content they write?",
"role": "user"
}
] | {"func_name": "verify_letter_frequency", "N": 24, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "a", "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Letter Frequency | In your response, the letter {letter} should appear {N} times. |
[
{
"content": "Your response must have 5 sections. Mark the beginning of each section with Chapter: X Please familiarize yourself with the following list of 99 categories. In a subsequent communication, you will be asked to use these categories for multiple-step grouping and sorting purposes. Please be sure to r... | {"func_name": "validate_sections", "N": 5, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": "Chapter:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "Answer with at least 35 sentences. Creatively image a question and justification for this answer: linen closet",
"role": "user"
}
] | {"func_name": "verify_sentence_constraint", "N": 35, "quantifier": "at least", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Sentences | Answer with at least / around / at most {N} sentences. |
[
{
"content": "First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) *Ans* yes\n*Question* Given the sentence \"Two women and a man are sitting at a blue table eating and drinking and smili... | {"func_name": "validate_repeat_prompt", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": "First, repeat the request witho... | ifeval | Repeat Prompt | First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) |
[
{
"content": "Some random thoughts: To answer the above question, the relevant sentence is: The modern game was developed on the other side of London by Middlesex cricket clubs, especially Teddington Hockey Club.\nGenerated quizz based on thoughtsQ: A game called hockey was played in English public schools in t... | {"func_name": "validate_two_responses", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Two Responses | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
[
{
"content": "Instruction:Compute the mean and standard deviation for this set of numbers.\n\nInput: 2, 3, 7, 5\n\n Entire output should be wrapped in JSON format.",
"role": "user"
}
] | {"func_name": "validate_json_format", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | JSON Format | Entire output should be wrapped in JSON format. |
[
{
"content": "Creatively image a question and justification for this answer: it is not possible to tell\n The response must contain at least 37 placeholders represented by square brackets, such as [address].",
"role": "user"
}
] | {"func_name": "validate_placeholders", "N": 37, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Placeholder | The response must contain at least {N} placeholders represented by square brackets, such as [address]. |
[
{
"content": "Q: 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 reaso... | {"func_name": "validate_frequency_capital_words", "N": 3, "quantifier": "at most", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Frequency of All-capital Words | In your response, words with all capital letters should appear at least / around / at most {N} times. |
[
{
"content": "Premise:\n\"The High-Minded Dismissal.\" Based on this premise, is the hypothesis \"Low minded dismissal \" true?\nOPTIONS:\n[1]. yes;\n[2]. it is not possible to tell;\n[3]. no; Include keywords raphiolepis, stumpiness in your response.",
"role": "user"
}
] | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["raphiolepis", "stumpiness"], "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Include Keywords | Include keywords {keyword1}, {keyword2} in your response. |
[
{
"content": "In your entire response, refrain from the use of any commas. Answer the following question:\n\nwho did the voice of the crab on moana?",
"role": "user"
}
] | {"func_name": "validate_no_commas", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | No Commas | In your entire response, refrain from the use of any commas. |
[
{
"content": "Teacher: In this task, you are given a sentence from the research paper and your task is to classify the given sentence into the following categories: Background (Why is this problem important? What relevant works have been created before? What is still missing in the previous works? What are the ... | {"func_name": "validate_word_constraint", "N": 21, "quantifier": "at most", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Words | Answer with at least / around / at most {N} words |
[
{
"content": "There should be 30 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The 7-th paragraph must start with word vaporary. 写一篇财务工作总结",
"role": "user"
}
] | {"func_name": "validate_paragraphs", "N": 30, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 7, "first_word": "vaporary", "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs + First Word in i-th Paragraph | There should be {N} paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The {i}-th paragraph must start with word {first word}. |
[
{
"content": "Your response should contain 26 paragraphs. You separate paragraphs using the markdown divider: * * * ¡Buenos días, princesa!",
"role": "user"
}
] | {"func_name": "verify_paragraph_count", "N": 26, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs | Your response should contain {N} paragraphs. You separate paragraphs using the markdown divider: * * * |
[
{
"content": "What are some up and coming and high quality youtube channels in science and technology that I have probably not heard of? Note that I am subscribed to close to 1000 channels. Your response should contain 17 paragraphs. You separate paragraphs using the markdown divider: * * *",
"role": "user"... | {"func_name": "verify_paragraph_count", "N": 17, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs | Your response should contain {N} paragraphs. You separate paragraphs using the markdown divider: * * * |
[
{
"content": "Your answer must contain exactly 11 bullet points. Use the markdown bullet points such as: * This is a point. How is a planet's orbital period determined?\n\nAnswer:",
"role": "user"
}
] | {"func_name": "verify_bullet_points", "N": 11, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Bullets | Your answer must contain exactly {N} bullet points. Use the markdown bullet points such as: * This is a point. |
[
{
"content": "Write a limmerick about the :NODDERS: emote Wrap your entire response with double quotation marks.",
"role": "user"
}
] | {"func_name": "validate_quotation", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Quotation | Wrap your entire response with double quotation marks. |
[
{
"content": "From Answer with one of the following options: yes/no/maybe Q: Complete:\nLONDON, England (CNN) -- A picture of an overweight woman lying naked on a couch, painted by British artist Lucian Freud, set a record Tuesday night for the most money paid for a painting by a living artist. \"Benefits Super... | {"func_name": "validate_choice", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": "yes/no/maybe", "section_splitter": null, "original_prompt": null} | ifeval | Choose | From Answer with one of the following options: {options} |
[
{
"content": "how do i create a form in jira that allows clients to create tickets First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence)",
"role": "user"
}
] | {"func_name": "validate_repeat_prompt", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": "how do i create a form in jira ... | ifeval | Repeat Prompt | First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) |
[
{
"content": "Denny asked: Premise: \"A woman with a flower in her hair sits by a man in a hat.\"\nBased on this premise, can we conclude that the hypothesis \"The woman is attracted to the man.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no.\nLe: OK, so how can I answer with some explanation?\... | {"func_name": "validate_title", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Title | Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
[
{
"content": "[Gestão da Cultura Organizacional para o Recursos Humanos de empresas em expansão que queiram dar direção à sua liderança, sabendo para onde e como crescer - Treinamento e Consultoria Empresarial] There should be 23 paragraphs. Paragraphs and only paragraphs are separated with each other by two li... | {"func_name": "validate_paragraphs", "N": 23, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 3, "first_word": "thermotension", "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs + First Word in i-th Paragraph | There should be {N} paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The {i}-th paragraph must start with word {first word}. |
[
{
"content": "Wrap your entire response with double quotation marks. R & A: A handstand is a move that has the whole body is off the ground except for one hand.\nyes\nQ: Premise: \"A person dancing is doing a dance move where there whole body is off the ground except for one hand.\"\nHypothesis: \"Someone is do... | {"func_name": "validate_quotation", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Quotation | Wrap your entire response with double quotation marks. |
[
{
"content": "You are given a background paragraph that describes one or more causal or qualitative relationships such as a relationship in economics or a scientific law and a story that makes use of the concepts or the relationship described in the provided paragraph. You need to come up with a question about ... | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["scalene", "nitidous"], "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Include Keywords | Include keywords {keyword1}, {keyword2} in your response. |
[
{
"content": "完成一個探究生活上自我管理的主題並用行動劇和聲音動作發表，一年級和二年級學生需要那些技能與哪些步驟? Answer with around 25 sentences.",
"role": "user"
}
] | {"func_name": "verify_sentence_constraint", "N": 25, "quantifier": "around", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Sentences | Answer with at least / around / at most {N} sentences. |
[
{
"content": "Please answer the following question: \"A Night of Thrills\", given a list of categories: company, educational institution, artist, athlete, office holder, mean of transportation, building, natural place, village, animal, plant, album, film or written work, what category does the title belong to?\... | {"func_name": "validate_lowercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Lowercase | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
[
{
"content": "Wrap your entire response with double quotation marks. Q: What would be the ★-rating of this review (★ being the lowest and ★★★★★ being the highest)? \"Excellent\"\nA: ★★★★★\n\n\nQ: What would be the ★-rating of this review (★ being the lowest and ★★★★★ being the highest)? \"It is a great app with... | {"func_name": "validate_quotation", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Quotation | Wrap your entire response with double quotation marks. |
[
{
"content": "Include keywords kevel, auricularia in your response. Using an Excel table, can you provide a detailed analysis of the advantages and disadvantages of market economies and planned economies?\nPlease include factors such as efficiency, innovation, income inequality, government control, and individu... | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["kevel", "auricularia"], "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Include Keywords | Include keywords {keyword1}, {keyword2} in your response. |
[
{
"content": "Denny asked: Can we conclude from \"The scientist is experimenting on the chicken eggs.\" that \"A man in a white lab coat is holding an egg.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell.\nLe: OK, so how can I answer with some explanation?\n Answer with around 28 words",
"role": "us... | {"func_name": "validate_word_constraint", "N": 28, "quantifier": "around", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Words | Answer with at least / around / at most {N} words |
[
{
"content": "Your response must have 38 sections. Mark the beginning of each section with Section: X Given the sentence \"A young woman in jeans and a gray sweater walks on the sidewalk in a shopping district.\" is it true that \"Young woman sitting in a cafe.\"? Stream of thoughts:",
"role": "user"
}
] | {"func_name": "validate_sections", "N": 38, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": "Section:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "A text is given in Hindi. Translate it from the Hindi language to the Urdu language. The translation must not omit or add information to the original sentence.\nExample: ہاؤسنگ اور شہری امور کی وزارت کے سکریٹری جناب درگا شنکر مشرا کی قیادت میں منعقدہ اس میٹنگ میں مجموعی طور پر 940 پروجیکٹوں کو منظ... | {"func_name": "validate_choice", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": "a), b), c), d)", "section_splitter": null, "original_prompt": null} | ifeval | Choose | From Answer with one of the following options: {options} |
[
{
"content": "As a TikTok content creator, you are tasked with promoting the SnugglePod Wearable Blanket for a company. Your objective is to create a table with the structure of two main columns - Action and Script - and rows comprising Hook, Problem 1, Problem 2, Product Intro/Solution, Benefit 1, Benefit 2, B... | {"func_name": "validate_lowercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Lowercase | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
[
{
"content": "Q: Read the following article and answer the question. Article: Bob Pearson is an old man. He has two big houses and a new car. He has no wife. But he is the father of four children. He has two sons and two daughters. One son is from England. His name is Bill. The other son is from America. His na... | {"func_name": "validate_lowercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Lowercase | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
[
{
"content": "The response must contain at least 13 placeholders represented by square brackets, such as [address]. Question:\nSolve -7*b + 399 = 4*b + 201 for b..\n\nAnswer:\n18\n\n\nQuestion:\nSolve 8*f - 15 = 3*f for f..\n\nAnswer:\n3\n\n\nQuestion:\nSolve -4607*l + 83996 = -1451*l + 662*l for l..\n\nAnswer:... | {"func_name": "validate_placeholders", "N": 13, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Placeholder | The response must contain at least {N} placeholders represented by square brackets, such as [address]. |
[
{
"content": "Entire output should be wrapped in JSON format. Question: Megan went to the store and bought a dozen eggs. When she got home, her neighbor gave her another dozen eggs from her chickens. Megan used 2 eggs to make an omelet for dinner and 4 eggs to bake a cake. When Megan's aunt came over for a visi... | {"func_name": "validate_json_format", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | JSON Format | Entire output should be wrapped in JSON format. |
[
{
"content": "Your answer must contain exactly 8 bullet points. Use the markdown bullet points such as: * This is a point. CVE description:\nExpat (aka libexpat) before 2.4.4 has a signed integer overflow in XML\\_GetBuffer, for configurations with a nonzero XML\\_CONTEXT\\_BYTES.\n\n취약점 발생 중인 함수:\nTfLiteIntArr... | {"func_name": "verify_bullet_points", "N": 8, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Bullets | Your answer must contain exactly {N} bullet points. Use the markdown bullet points such as: * This is a point. |
[
{
"content": "Your entire response should be in English, capital letters only. In this task, you need to rewrite the given long sentence into two smaller sentences.\nJohn had always wanted to go on vacation to Europe but his parents couldn't afford it.",
"role": "user"
}
] | {"func_name": "validate_uppercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Uppercase | Your entire response should be in English, capital letters only. |
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you need to answer 'Yes' if the given word is the longest word (in terms of number of letters) in the given sentence, else answer 'No'. Note that there could be m... | {"func_name": "validate_lowercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Lowercase | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
[
{
"content": "Write a script that downloads videos on Bilibili website. The script accepts URLs as input and outputs video files. Your entire response should be in English, capital letters only.",
"role": "user"
}
] | {"func_name": "validate_uppercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Uppercase | Your entire response should be in English, capital letters only. |
[
{
"content": "Your answer must contain exactly 35 bullet points. Use the markdown bullet points such as: * This is a point. Problem: Given the question: What type of details about adelaide of meissen can be gathered from the following bio? Bio: adelaide of meissen -lrb- , ; c. 1160 -- 2 february 1211 -rrb- wa... | {"func_name": "verify_bullet_points", "N": 35, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Bullets | Your answer must contain exactly {N} bullet points. Use the markdown bullet points such as: * This is a point. |
[
{
"content": "Your entire response should be in English, capital letters only. What was the question for this implicit rationale, and corresponding answer?\nHe saved money for 2 years, which is equal to 12 x 2 = 24 months. The amount of money he saved is $25 * 24 = $600. But he spent some money so there is $600... | {"func_name": "validate_uppercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Uppercase | Your entire response should be in English, capital letters only. |
[
{
"content": "Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Can you create an email with HTML code that promotes GrooveFunnels and written in a conversational, witty, and intriguing manner, inspired by the writing styles of Dan Kennedy, Gary Bencivenga, and Clayt... | {"func_name": "validate_title", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Title | Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
[
{
"content": "In MCTS with nodes and simulated annealing, have you ever encountered the concept of \"backpropagation speed\" while considering the influence of temperature changes on the algorithm efficiency? Your response must have 13 sections. Mark the beginning of each section with Chapter: X",
"role": "... | {"func_name": "validate_sections", "N": 13, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": "Chapter:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "Question:\nWrite a sentence not in English.\nSentence:\nLe directeur de l’enregistrement des armes à feu est nommé par le commissaire.\n-+-+-+-\nQuestion:\nWrite a sentence not in English.\nSentence:\nCette question relève des plans d’organisation des écoles que les Autorités locales de l’éducatio... | {"func_name": "verify_sentence_constraint", "N": 35, "quantifier": "at least", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Sentences | Answer with at least / around / at most {N} sentences. |
[
{
"content": "[Q]: \"Begin to develop a comprehensive set of performance indicators that can be used to measure First Nations police effectiveness over the longer term.\" --> French?\n[A]: Amorcer l'élaboration d'un ensemble complet d'indicateurs de rendement afin de mesurer l'efficacité à long terme de la poli... | {"func_name": "validate_lowercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Lowercase | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
[
{
"content": "Given the following reasoning and answer, what was the question? Having a suit and being at a podium doesn't mean the old man is giving a speech.\n The answer: it is not possible to tell\n At the end of your response, please explicitly add a postscript starting with PS:",
"role": "user"
}
] | {"func_name": "verify_postscript", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": "PS:", "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Postscript | At the end of your response, please explicitly add a postscript starting with {postscript marker} |
[
{
"content": "Your response must have 4 sections. Mark the beginning of each section with Section: X Given the sentence \"A lady wearing a black dress and with sunglasses is talking on the phone.\" can we conclude that \"A lady wearing a black dress and with sunglasses is talking on the phone in the park.\"?\nO... | {"func_name": "validate_sections", "N": 4, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": "Section:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "Please answer this: Here's a complex question that requires someone to reason about the input, can you answer it? Tianyi Film Company's Hong Kong studio became successful under the leadership of the founder of which dominant TV company?\n++++++++\nAnswer: TVB\n\n\nPlease answer this: Here's a comp... | {"func_name": "verify_letter_frequency", "N": 10, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "e", "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Letter Frequency | In your response, the letter {letter} should appear {N} times. |
[
{
"content": "Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. Premise: \"Two men in keffiyahs stand next to car in the desert and wave at a passing vehicle.\"\nHypothesis: \"Two men are standing next to a car that is broken down.\"\nIs the hypothe... | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "That's all I have to say.", "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | End Checker | Finish your response with this exact phrase {end phrase}. No other words should follow this phrase. |
[
{
"content": "Select the most appropriate synonym.\nEnormous\nA. Monstrous\nB. Tiny\nC. Magnificent\nD. Robust\n\n Your answer must contain exactly 20 bullet points. Use the markdown bullet points such as: * This is a point.",
"role": "user"
}
] | {"func_name": "verify_bullet_points", "N": 20, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Bullets | Your answer must contain exactly {N} bullet points. Use the markdown bullet points such as: * This is a point. |
[
{
"content": "At the end of your response, please explicitly add a postscript starting with PS: Q: En précisant le champ d'application du Règlement no 94 dans son titre et dans son paragraphe 1.2, on éviterait donc le risque de violation de l'Accord de 1958.... English?\nA: [For this reason, the possibility of ... | {"func_name": "verify_postscript", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": "PS:", "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Postscript | At the end of your response, please explicitly add a postscript starting with {postscript marker} |
[
{
"content": "Find the total cost of 3 items priced at $10, $25 and $50\nResponse: In your response, the letter h should appear 17 times.",
"role": "user"
}
] | {"func_name": "verify_letter_frequency", "N": 17, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "h", "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Letter Frequency | In your response, the letter {letter} should appear {N} times. |
[
{
"content": "como calificarías esta frase:\nO estás conmigo o estás contra mi. There should be 34 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The 25-th paragraph must start with word wadi.",
"role": "user"
}
] | {"func_name": "validate_paragraphs", "N": 34, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 25, "first_word": "wadi", "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs + First Word in i-th Paragraph | There should be {N} paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The {i}-th paragraph must start with word {first word}. |
[
{
"content": "Can node.js request.on('close') be used to detect if a request disconnected prematurely Your response should contain 2 paragraphs. You separate paragraphs using the markdown divider: * * *",
"role": "user"
}
] | {"func_name": "verify_paragraph_count", "N": 2, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs | Your response should contain {N} paragraphs. You separate paragraphs using the markdown divider: * * * |
[
{
"content": "#Rewritten Prompt#:\r\nYou are tasked with converting a JSON file containing a table into an XML file using Python. Your script must handle nested objects and arrays within the JSON file and preserve any special characters or formatting within the table data. Additionally, you must ensure that the... | {"func_name": "validate_uppercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Uppercase | Your entire response should be in English, capital letters only. |
[
{
"content": "Fontaine Charles-Péguy , Square Alain Gilot , rue Montempoivre 1989 , Charles Péguy , architect , and Liliane Grunig Tribel , landscape architect .\nFontaine Charles - Péguy , Square Charles Péguy , rue Montempoivre 1989 , architect Alain Gilot , and Liliane Grunig Tribel , landscape architect .\n... | {"func_name": "validate_paragraphs", "N": 18, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 6, "first_word": "whaling", "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs + First Word in i-th Paragraph | There should be {N} paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The {i}-th paragraph must start with word {first word}. |
[
{
"content": "The response must contain at least 5 placeholders represented by square brackets, such as [address]. [Choose the sentence that goes against common sense.\nOptions:\n- Sentence A: \"He ate a hamburger for dinner.\"\n- Sentence B: \"He ate a wrench for dinner.\"\n]\n\nMy step-by-step solution: A wre... | {"func_name": "validate_placeholders", "N": 5, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Placeholder | The response must contain at least {N} placeholders represented by square brackets, such as [address]. |
[
{
"content": "Finish your response with this exact phrase Oh no.. No other words should follow this phrase. Q: Which of the following sentences is nonsensical?\nOptions:\n- Sentence A: \"Alcohol can not disinfect\"\n- Sentence B: \"Alcohol can disinfect\"\n\nLet's solve this gradually.",
"role": "user"
}
... | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "Oh no.", "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | End Checker | Finish your response with this exact phrase {end phrase}. No other words should follow this phrase. |
[
{
"content": "A woman can't be standing and occupying a bench at the same time.\nThe question and answer are below.\nPremise: \"A city street with a metal bench occupied by a woman in black.\"\nBased on this premise, can we conclude that the hypothesis \"A woman standing in the rain.\" is true?\nOptions:\n- yes... | {"func_name": "validate_highlighted_sections", "N": 27, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Minimum Number Highlighted Section | Highlight at least {N} sections in your answer with markdown, i.e. *highlighted section* |
[
{
"content": "Do not include keywords counterreligion, bricklayer, huttoning in the response. Q: Premise: \"A blond woman dances on a sunny day.\"\nHypothesis: \"A blond woman is happy she won the lottery so she dances.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell... | {"func_name": "validate_forbidden_words", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": ["counterreligion", "bricklayer", "huttoning"], "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "origin... | ifeval | Forbidden Words | Do not include keywords {forbidden words} in the response. |
[
{
"content": "Question: yeah what you know what's really funny um is that i get calls you know mostly telephone sales people that i just you know that want to start beating my ear you know\nI don't mind telephone sales people.\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nAnswer: no\n\nQuestion: He wa... | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "That's all.", "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | End Checker | Finish your response with this exact phrase {end phrase}. No other words should follow this phrase. |
[
{
"content": "As the man descended the mountains into the marsh, where was he?\nOptions:\n- louisiana\n- florida\n- everglades\n- field\n- low lands\nLet's think now! Step-by-step reasoning: Your response should contain 7 paragraphs. You separate paragraphs using the markdown divider: * * *",
"role": "user"... | {"func_name": "verify_paragraph_count", "N": 7, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs | Your response should contain {N} paragraphs. You separate paragraphs using the markdown divider: * * * |
[
{
"content": "Question:\nJeremic: Serbia va solicita aderarea la UE anul acesta\n\nCould you please translate this to English?\nAnswer:\nJeremic: Serbia will apply for EU membership this year\ntest: Nu mai este nevoie să spun că nu trebuie sacrificată siguranţa de dragul obiectivelor ecologice, drept pentru car... | {"func_name": "validate_no_commas", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | No Commas | In your entire response, refrain from the use of any commas. |
[
{
"content": "In your response, the word professively should appear 26 times. Question:\nSummarize this: former formula one and cart champion jacques villeneuve will make his debut in nascar 's second-tier series nationwide on saturday on a very familiar track .\nAnswer:\nvilleneuve set for nationwide debut\nQu... | {"func_name": "verify_keyword_frequency", "N": 26, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "professively", "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Keyword Frequency | In your response, the word {word} should appear {N} times. |
[
{
"content": "There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The 1-th paragraph must start with word gnatling. You need to complete the following task:\n\nCreate an SQL query that lists the employee names with their corresponding department and sal... | {"func_name": "validate_paragraphs", "N": 2, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 1, "first_word": "gnatling", "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs + First Word in i-th Paragraph | There should be {N} paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The {i}-th paragraph must start with word {first word}. |
[
{
"content": "Answer with at most 31 sentences. Does the following sentence make sense?\n\"Boron radiates heat, and can be harmful to people not wearing protective gear.\"\nOptions:\n- yes\n- no\nno\nBoron is not radioactive, but still should be treated with respect because it is used as a research agent.\n**Q*... | {"func_name": "verify_sentence_constraint", "N": 31, "quantifier": "at most", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Sentences | Answer with at least / around / at most {N} sentences. |
[
{
"content": "Question: Information: - The Space Shuttle was a partially reusable low Earth orbital spacecraft system operated by the U.S. National Aeronautics and Space Administration (NASA), as part of the Space Shuttle program. Its official program name was \"Space Transportation System (STS)\", taken from ... | {"func_name": "validate_quotation", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Quotation | Wrap your entire response with double quotation marks. |
[
{
"content": "Your response should contain 3 paragraphs. You separate paragraphs using the markdown divider: * * * if i am adding an object as a key in dict what exactly considered as unique thing in that obj",
"role": "user"
}
] | {"func_name": "verify_paragraph_count", "N": 3, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs | Your response should contain {N} paragraphs. You separate paragraphs using the markdown divider: * * * |
[
{
"content": "Your answer must contain exactly 26 bullet points. Use the markdown bullet points such as: * This is a point. Q: If RECOMMENDED REPORTING, can we say that \"Not recommended reporting\"?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nA: no\nPremise:\n\"so even some aspects of recycling\"\n... | {"func_name": "verify_bullet_points", "N": 26, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Bullets | Your answer must contain exactly {N} bullet points. Use the markdown bullet points such as: * This is a point. |
[
{
"content": "The response must contain at least 10 placeholders represented by square brackets, such as [address]. Can you develop an intricate and captivating rap battle between two fiercely skilled Age of Empires 2 competitors with distinct and opposing strengths in warfare? The first player is a master of a... | {"func_name": "validate_placeholders", "N": 10, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Placeholder | The response must contain at least {N} placeholders represented by square brackets, such as [address]. |
[
{
"content": "Finish your response with this exact phrase That's it.. No other words should follow this phrase. You are a scientific research assistant. You will be shown a passage from a medical clinical trial report. Your task is to extract all the findings from this report into a JSON array. A single finding... | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "That's it.", "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | End Checker | Finish your response with this exact phrase {end phrase}. No other words should follow this phrase. |
[
{
"content": "Recommend a good book and explain why it is so good.\n\n Your response must have 10 sections. Mark the beginning of each section with Chapter: X",
"role": "user"
}
] | {"func_name": "validate_sections", "N": 10, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": "Chapter:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "Given the rationale, provide a reasonable question and answer. Step-by-step reasoning process: Although the man is posing with an axe there is no mention of a halloween costume contest.\n The question and answer: Give two different responses. Responses and only responses should be separated by 6 a... | {"func_name": "validate_two_responses", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Two Responses | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
[
{
"content": "*Question*\nTitle: Not happy, returned toy. Not worth it! Product review: The idea is nice, but it drained a fresh batch of batteries within a couple of days and not that much use. Features were not that great either. Totally not worth it in my opinion. Very dissapointed.I have tried other product... | {"func_name": "validate_no_commas", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | No Commas | In your entire response, refrain from the use of any commas. |
[
{
"content": "学校的乐队有女生18人，男生17人。合唱队的人数是乐队的3倍，合唱队有多少人？ Answer with at least 29 words",
"role": "user"
}
] | {"func_name": "validate_word_constraint", "N": 29, "quantifier": "at least", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Words | Answer with at least / around / at most {N} words |
[
{
"content": "In your response, the letter a should appear 24 times. Answer a question about this article:\nIncreasingly, more modern games such as video games and slot machines are provided. Pubs hold special events, from tournaments of the aforementioned games to karaoke nights to pub quizzes. Some play pop m... | {"func_name": "verify_letter_frequency", "N": 24, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "a", "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Letter Frequency | In your response, the letter {letter} should appear {N} times. |
[
{
"content": "Informed consent is a technical term first used by attorney, Paul G. Gebhard, in a medical malpractice United States court case in 1957. In tracing its history, some scholars have suggested tracing the history of checking for any of these practices:\n\nAnswer this question: where did the concept o... | {"func_name": "validate_two_responses", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Two Responses | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
[
{
"content": "Your entire response should be in English, capital letters only. ** Intersection is a point at which two or more things intersect, especially a road junction. Street corners are on road junctions. People are likely to stand at street corners at an intersection.\nstreet corner\n** Where are people ... | {"func_name": "validate_uppercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Uppercase | Your entire response should be in English, capital letters only. |
[
{
"content": "The response must contain at least 26 placeholders represented by square brackets, such as [address]. Generate a movie review based on this synopsis of Little Women\n\nThe film follows the classic novel by Louisa May Alcott and tells the story of the four March sisters who come of age in America i... | {"func_name": "validate_placeholders", "N": 26, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Placeholder | The response must contain at least {N} placeholders represented by square brackets, such as [address]. |
[
{
"content": "input question: Question: The man was disheveled and wanted to clean clothes, so what was he hoping to achieve? Options: - attractive appearance - look better - sanitation - clean clothes - laundromat Explain why a human would choose \"look better\" to answer the question above:???\noutput answer... | {"func_name": "validate_forbidden_words", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": ["deracialize", "swilltub", "pareioplitae"], "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_... | ifeval | Forbidden Words | Do not include keywords {forbidden words} in the response. |
[
{
"content": "Include keywords lad, filator in your response. Given the flower dataset with details such as petal length, petal width, sepal length, and sepal width, write a Python code that groups the data by species, computes the mean petal length for each species, and further filters the data by considering ... | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["lad", "filator"], "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Include Keywords | Include keywords {keyword1}, {keyword2} in your response. |
[
{
"content": "There should be 22 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The 18-th paragraph must start with word pepsinhydrochloric. Can you provide a comprehensive comparison of the performance and scalability of Apache Spark, Apache Flink, and Dask framewo... | {"func_name": "validate_paragraphs", "N": 22, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 18, "first_word": "pepsinhydrochloric", "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs + First Word in i-th Paragraph | There should be {N} paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The {i}-th paragraph must start with word {first word}. |
[
{
"content": "In your response, the letter d should appear 36 times. You are given a sentence in Italian. Your job is to translate the Italian sentence into English.\n\nQ: Si trattava semplicemente di annotare i vari compiti svolti dai diversi AD e di annotare il tempo impiegato per effettuare le relative scelt... | {"func_name": "verify_letter_frequency", "N": 36, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "d", "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Letter Frequency | In your response, the letter {letter} should appear {N} times. |
[
{
"content": "Generate a 5-star review (1 being lowest and 5 being highest) about an app with package com.google.android.gms.\n----\nAnswer: Love too Much\n\n\nGenerate a 1-star review (1 being lowest and 5 being highest) about an app with package com.fsck.k9.\n----\nAnswer: WAS good :( :( :( Used K-9 for sever... | {"func_name": "validate_placeholders", "N": 17, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Placeholder | The response must contain at least {N} placeholders represented by square brackets, such as [address]. |
[
{
"content": "In addition to the existing requirements, how can the deep learning model handle imbalanced datasets and incorporate reinforcement learning techniques to further enhance its performance? How can the model be made more robust to changes in writing styles and lighting conditions, while also taking i... | {"func_name": "validate_two_responses", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Two Responses | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
[
{
"content": "Task: Create a JavaScript function to find the second smallest number in an array\n\n[5, 10, 15, 20]\n\nAnswer: In your response, words with all capital letters should appear around 37 times.",
"role": "user"
}
] | {"func_name": "validate_frequency_capital_words", "N": 37, "quantifier": "around", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Frequency of All-capital Words | In your response, words with all capital letters should appear at least / around / at most {N} times. |
[
{
"content": "Task: Write a Java program to print all the Fibonacci series between 0 to 50.\n\n Your entire response should be in English, capital letters only.",
"role": "user"
}
] | {"func_name": "validate_uppercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Uppercase | Your entire response should be in English, capital letters only. |
[
{
"content": "Given the below context: Set in Chicago in the 1930s, Bigger Thomas, an African American who lives in an impoverished neighborhood, is employed by a prosperous white family who live in the suburbs of a major city. The money Bigger makes at his new job will be used to supplement his mother's incom... | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["macrodactylic", "nonfiction"], "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Include Keywords | Include keywords {keyword1}, {keyword2} in your response. |
[
{
"content": "How many pineapples can fit into a suitcase? Make reasonable assumptions. Use metric. Wrap your entire response with double quotation marks.",
"role": "user"
}
] | {"func_name": "validate_quotation", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Quotation | Wrap your entire response with double quotation marks. |
[
{
"content": "Finish your response with this exact phrase That's crazy.. No other words should follow this phrase. Q: \"Fish without scales, shellfish and crustaceans are only accepted by some Muslim groups.\" to French\n****\nA: Les poissons sans écaille, les mollusques et les crustacés ne sont acceptés que pa... | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "That's crazy.", "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | End Checker | Finish your response with this exact phrase {end phrase}. No other words should follow this phrase. |
[
{
"content": "Suppose a hydropower plant generates electricity using water flow. If the water flow rate is 5m³/s and the water head is 20m, what is the power output in watts? Remember that the efficiency of the turbine is 80% and the acceleration due to gravity is 9.81m/s². Provide your answer to the nearest wh... | {"func_name": "validate_quotation", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Quotation | Wrap your entire response with double quotation marks. |
[
{
"content": "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\nCompose an if-else block in Python for checking if a string is empty.\n\n### Input:\nstr1 = \"My String\"\nstr2 = \"\"\... | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "That's crazy.", "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | End Checker | Finish your response with this exact phrase {end phrase}. No other words should follow this phrase. |
[
{
"content": "First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) Denny asked: Premise: \"A crowd of people looking towards a person in a gorilla costume inside a building.\"\nBased on t... | {"func_name": "validate_repeat_prompt", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": "First, repeat the request witho... | ifeval | Repeat Prompt | First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) |
[
{
"content": "In your entire response, refrain from the use of any commas. Does the following sentence make sense?\n\"Like Nostradamas, George Orwell has been able to predict future events perfectly through his book Nineteen Eighty-Four.\"\nOptions:\n- yes\n- no\nno\nGeorge Orwell never claimed to be a prophet,... | {"func_name": "validate_no_commas", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | No Commas | In your entire response, refrain from the use of any commas. |
[
{
"content": "Q: Given this review: \"Why cant i remove this app Why cant i remove this app\" Would you recommend this app to a friend? Not at all, No, Maybe, Yes, or Definitely?\nA: Not at all\n\n\nQ: Given this review: \"Great idea behind this! Having a widget that allows several apps to have access to the wi... | {"func_name": "validate_placeholders", "N": 8, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Placeholder | The response must contain at least {N} placeholders represented by square brackets, such as [address]. |
[
{
"content": "Your response should contain 13 paragraphs. You separate paragraphs using the markdown divider: * * * What are the pro`s, con`s and risks of using https://questdb.io/\" as a time series db compared to other popular solutions ? Please also include at least 5 other solutions and discuss their streng... | {"func_name": "verify_paragraph_count", "N": 13, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs | Your response should contain {N} paragraphs. You separate paragraphs using the markdown divider: * * * |
[
{
"content": "In your entire response, refrain from the use of any commas. Problem: Write a positive (OPTIONS:\n- negative\n- positive) yelp review.\nA: I came here for a friend's birthday a couple weeks ago. The lamb tandoori burger is great! The vidalia onion rings are very good. Not too heavy on the batte... | {"func_name": "validate_no_commas", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | No Commas | In your entire response, refrain from the use of any commas. |
[
{
"content": "[QUESTION] Given the sentence \"A man wearing a gray coat.\" can we conclude that \"Black hat and gloves drives a red and white carriage being drawn by two white horses.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nThe man wearing clothes is sitting on top of a white horse.\nThe answer... | {"func_name": "verify_bullet_points", "N": 20, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Bullets | Your answer must contain exactly {N} bullet points. Use the markdown bullet points such as: * This is a point. |
[
{
"content": "Wrap your entire response with double quotation marks. The fact that in the city a lady and man are on their phone while an Indian couple pass by does not imply that they waves at an indian couple.\nThis justifies what answer for what question? Q & A:",
"role": "user"
}
] | {"func_name": "validate_quotation", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Quotation | Wrap your entire response with double quotation marks. |
[
{
"content": "This is a correct answer to the following question about Meister. Yes or no? Answer: In sports, Meister is used for the current national, European or world champion (Deutscher Meister, *Europameister, Weltmeister). Question: What does the name \"Meister\" mean in German\nNo\n------\nThis is a corr... | {"func_name": "verify_postscript", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": "PS:", "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Postscript | At the end of your response, please explicitly add a postscript starting with {postscript marker} |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.