messages listlengths 1 1 | ground_truth stringlengths 285 19k | dataset stringclasses 1
value | constraint_type stringclasses 24
values | constraint stringclasses 24
values |
|---|---|---|---|---|
[
{
"content": "You will be shown sections from a scientific research paper, together with a question about the paper. Please print out a collection of quotations from the research paper which answer the question. Each quotation should be a contiguous span of text from the paper. Separate the quotations with newl... | {"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": "Your entire response should be in English, capital letters only. [QUESTION] Can we conclude from \"Person in kayak with water splashing up and over person and kayak.\" that \"A person is outside getting wet.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA person outside getting wet coul... | {"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": "Write a letter to my childhood friend, Barbara, whose nickname was Barbie. My name is Scott. We see each other a few times a year. Tell her we'd love to see them soon! We loved to skateboard in elementary school. She love alternative music. I played tennis. She was like a sister to me. We've known... | {"func_name": "verify_bullet_points", "N": 28, "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. Person A: A fencing thrust with a sharp sword towards a person would result in what?\nOptions:\n- injury\n- small cuts\n- fever\n- competition\n- puncture wound\nPerson B: Let me think. Sudden attack in fencing by pushing sword can hurt the op... | {"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": "Given the task definition and input, reply with output. Given a sentence, generate a new 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 p... | {"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": "input: Please answer the following: Build a movie plot around this: Where does Eddie go to track Snakehead ? Hong Kong\n++++++++++\noutput: Eddie Yang (Jackie Chan) is a Hong Kong police inspector co-operating with Interpol in the capture of a crime lord named AJ \"Snakehead\" Staul (Julian Sands)... | {"func_name": "validate_word_constraint", "N": 26, "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": "Highlight at least 15 sections in your answer with markdown, i.e. *highlighted section* Come up with three questions for an AI-based virtual assistant with a health-related focus. Output:",
"role": "user"
}
] | {"func_name": "validate_highlighted_sections", "N": 15, "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": "In your response, the letter f should appear 25 times. Given the following reasoning and answer, what was the question? A game machine cannot be used to communicate.\n The answer: Sentence A",
"role": "user"
}
] | {"func_name": "verify_letter_frequency", "N": 25, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "f", "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": "The motorcycle racer leaning over on a turn assumes they are on a motorcycle.\nThe question and answer are below.\nPremise: \"A motorcycle racer leaning over to take a sharp turn.\"\nBased on this premise, can we conclude that the hypothesis \"A man is racing a motorcycle.\" is true?\nOptions:\n- ... | {"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": "Before I forget:", "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": "Include keywords bibasic, fishmonger in your response. Question: What would be the ★-rating of this review (★ being the lowest and ★★★★★ being the highest)? \"Good jobs team\"\nAnswer: ★★★★★\n\nQuestion: What would be the ★-rating of this review (★ being the lowest and ★★★★★ being the highest)? \"... | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["bibasic", "fishmonger"], "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": "[Question]Maddie wants to see how much her mom spends on coffee each week. She makes herself 2 cups of coffee per day. Each cup has 1.5 ounces of coffee beans. A bag of coffee costs $8 and contains 10.5 ounces of beans. She uses 1/2 a gallon of milk per week. A gallon of milk costs $4. She doesn't... | {"func_name": "verify_letter_frequency", "N": 3, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "b", "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": "Test for natural language inference.\nPremise: \"The people have paint on them.\"\nHypothesis: \"The people are painting a mural.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell Let's be accurate as possible and think first.\n In your entire respo... | {"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": "Entire output should be wrapped in JSON format. The dancers are getting ready and ready imply the same thing.\nThis justifies what answer for what question? Q & A:",
"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": "Highlight at least 28 sections in your answer with markdown, i.e. *highlighted section* Tell me how would you respond to the following request.\nDescribe how two people can cooperate to solve a problem.",
"role": "user"
}
] | {"func_name": "validate_highlighted_sections", "N": 28, "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": "Entire output should be wrapped in JSON format. Please capitalize where necessary: 2 years ago 3:01:19 redtube double anal, interracial, double penetration, two cocks in the booty",
"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": "If \"An old couple stands with their back to a statue of two lovers.\" does that mean that \"A couple standing near a statue.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no A step-by-step solution is:\n In your response, the word sailplane should appear 13 times.",
"role": "user"
}
... | {"func_name": "verify_keyword_frequency", "N": 13, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "sailplane", "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": "Problem: Given the background: Rainfall in an area is important because it influences the rate of weathering. More rain means that more rainwater passes through the soil. The rainwater reacts chemically with the particles. The top layers of soil are in contact with the freshest water, so reactions... | {"func_name": "validate_placeholders", "N": 6, "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": "Yes / no, is the following a verifiable fact?\n\"Hildegard of Bingen vanished during a solo airplane flight through the Bermuda Triangle.\"\nno\nAmelia Erhardt, not Hildegard of Bingen, is believed by some to have disappeared in the Bermuda Triangle.\n**Q**\nIs the following statement true?\n\"Pyt... | {"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": "¿Cuál es la universidad de mayor prestigio en Madrid para estudiar ADE? 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": "Answer with at most 17 sentences. I want to test the ability of students to read a passage and answer questions about it. Could you please come up with a good question for the passage \"Between 1832 and 2002 the currency of Greece was the drachma. After signing the Maastricht Treaty, Greece applie... | {"func_name": "verify_sentence_constraint", "N": 17, "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": "Write a script for a customer talking to a customer support representative.\n\nThe customer needs help setting up their printer.\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": "Rewrite the following sentence using the opposite: They punished him for being irresponsible.\n\nThey punished him for being irresponsible.\n\n Your response must have 15 sections. Mark the beginning of each section with Part: X",
"role": "user"
}
] | {"func_name": "validate_sections", "N": 15, "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": "Part:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "IN: PM pushes Putin on Syria ceasefire\nPrime Minister Malcolm Turnbull has urged President Vladimir Putin to pressure Russia's ally Syria to reinstate and abide by a ceasefire.\n\nMr Turnbull says Russia has the critical influence to help ensure the Assad regime complies with a new ceasefire afte... | {"func_name": "verify_letter_frequency", "N": 21, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "b", "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": "Parse the following string to obtain all the digits.\n\nAdditional Context:\nstr1 = \"Price of the product is $128.\"\n\nAnswer: Answer with around 11 words",
"role": "user"
}
] | {"func_name": "validate_word_constraint", "N": 11, "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": "My question is: A company is lining a 900-foot path with a fence. Every 6 feet, a fence pole is placed. The entire path is lined with a fence except for a 42-foot bridge. How many fence poles will be placed along the whole path on both sides? Your thoughts: In your response, words with all capital... | {"func_name": "validate_frequency_capital_words", "N": 21, "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 | Frequency of All-capital Words | In your response, words with all capital letters should appear at least / around / at most {N} times. |
[
{
"content": "Can you provide a comprehensive comparison of the performance and scalability of Apache Spark, Apache Flink, and Dask frameworks? Additionally, could you elaborate on the specific use cases in which each framework is most effective, as well as the benefits and limitations of each? At the end of yo... | {"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": "Before I forget:", "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 answer must contain exactly 19 bullet points. Use the markdown bullet points such as: * This is a point. IN: French:\n\nThe Service Canada initiative will help us to address the access challenge.\nOUT: L'initiative Service Canada nous aidera à relever le défi de l'accès.\nIN: French:\n\n3 - 6... | {"func_name": "verify_bullet_points", "N": 19, "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": "In your response, words with all capital letters should appear at least 29 times. In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic... | {"func_name": "validate_frequency_capital_words", "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 | 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 There should be 13 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The 6-th paragraph must start with word skippership.",
"role": "user"
}
] | {"func_name": "validate_paragraphs", "N": 13, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 6, "first_word": "skippership", "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": "From Answer with one of the following options: I know or I don't know Write a response that appropriately completes the request.\n\n### Instruction:\nWrite a function in C# to insert a character into a string at a given index.\n\n### Response:",
"role": "user"
}
] | {"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": "I know or I don't know", "section_splitter": null, "original_prompt": null} | ifeval | Choose | From Answer with one of the following options: {options} |
[
{
"content": "Instruction:Create the HTML component for a form field.\n\nInput: Field Name: First Name\nField Type: Text\n\n Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
] | {"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": "In your entire response, refrain from the use of any commas. Premise: \"The brown dog is running across the sand.\"\nHypothesis: \"The dog is running on the beach.\"\nDo we know that the hypothesis entailed by the premise? A step-by-step solution is:",
"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": "The man is leaning against another man which implies the men are touching.\nThe question and answer are below.\nCan we conclude from \"A man leaning against another man with his eyes closed.\" that \"The two men are touching.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nyes\n\nUnsure o... | {"func_name": "verify_sentence_constraint", "N": 26, "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": "Problem: On a scale of 1-5 (with 1 being least favorable and 5 being most favorable), how would you rate this review? \"A must for the modem Internet user This is a critical piece of software that will increase your security by 100x over just using traditional passwords.\"\n\nA: 5\n\n\nProblem: On... | {"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": "um-hum it it with the children's aspect um-hum\n\nDoes it follow that \"I somewhat agree about this particular topic as it relates to children.\"? Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
] | {"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": "Explanation for the following question's answer: A fox has 4 legs and cannot fly.\nQuestion: Of the following two sentences, which one is against common sense?\nOptions:\n- Sentence A: \"A fox is a bird\"\n- Sentence B: \"A fox is an animal\"\n\nAnswer: Sentence A\nChain-of-thought: A dishwashers ... | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["beyship", "tormenta"], "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": "解答这个题：To determine the mean number of children per\nhousehold in a community, Tabitha surveyed\n20 families at a playground. For the 20 families\nsurveyed, the mean number of children per\nhousehold was 2.4. Which of the following\nstatements must be true?\nA) The mean number of children per house... | {"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": "Entire output should be wrapped in JSON format. input question: Write a multi-choice question for the following article: Article: There are lots of animals on the earth. What is the biggest animal of all? The whale is. A blue whale weighs more than a hundred tons. Whales live in the sea, but they... | {"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": "**Q**\nYes / no, is the following a verifiable fact?\n\"Marvel Comics has gone from printing to full blown motion pictures since its beginnings in the early 20th century.\"\n**A**\nyes\nMarvel Comics found huge success with the 2008 Iron Man movie which then launched the MCU which has grossed bill... | {"func_name": "verify_paragraph_count", "N": 19, "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 response, words with all capital letters should appear around 5 times. Premise & hypothesis.\nA man using a shovel to dig a hole.\n\na man is building something\n++++++++++\ntrue or not.\nno\n\n\nPremise & hypothesis.\nA lady holds a harp in the woods.\n\nA lady is wearing a brooch while h... | {"func_name": "validate_frequency_capital_words", "N": 5, "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": "From Answer with one of the following options: yes/no/maybe The kingdom of Assam was the last conquest of Bodawpaya. In December 1816, he sent a 16,000-strong force to Assam to install his nominee, Chandra Kanta Singh, to the Assamese throne. From their northernmost forts in Hukawng Valley in pres... | {"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": "In your response, the word earnie should appear 25 times. Is this product review positive? Title: I was both haunted and inspired. Review: This is one of those books you will never forget. Filled with kindness, desperation, yearning, charity, fear, faith, and love, it will leave you haunted and in... | {"func_name": "verify_keyword_frequency", "N": 25, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "earnie", "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": "Question and Answer: Of the below sentences, which one does *not* make sense?\nOptions:\n- Sentence A: \"Roses are pretty chickens\"\n- Sentence B: \"Roses are pretty flowers\"\n\nSentence A\nSome idea for the solution: Roses are plants and chickens are animals and these are two seperate groups.\n... | {"func_name": "validate_word_constraint", "N": 11, "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 25 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The 3-th paragraph must start with word tapalo. (Question)\nGiven this review: \"Awesome☺☺😊🎂\" Would you recommend this app to a friend? Not at all, No, Maybe, Yes, or Definitely?\n(An... | {"func_name": "validate_paragraphs", "N": 25, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 3, "first_word": "tapalo", "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": "Finish your response with this exact phrase Oh no.. No other words should follow this phrase. QUESTION: If \"Two men and a woman standing at the bottom of a cliff face.\" does that mean that \"3 people eat at a restaurant.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it s... | {"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": "Quiero que me proporciones un script en python que calcule el número primo que ocupa la posición 10.000 y que se ejecute en el menor tiempo posible Include keywords coseismal, gogo in your response.",
"role": "user"
}
] | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["coseismal", "gogo"], "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 response, the letter c should appear 10 times. You need to complete the following task:\n\nClassify the words \"slide\" and \"jog\" as verbs or nouns.",
"role": "user"
}
] | {"func_name": "verify_letter_frequency", "N": 10, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "c", "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": "In your response, the letter j should appear 39 times. SEOUL — The head of the United Nations World Food Program (WFP) on Tuesday said the North Korean leadership is hopeful that following a possible denuclearization deal, the international community will increase humanitarian aid for millions of ... | {"func_name": "verify_letter_frequency", "N": 39, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "j", "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": "In your entire response, refrain from the use of any commas. First find how thick the blanket will be after 1 folding: 3 inches * 2 = 6 inches. Then find how thick the blanket will be after 2 foldings: 6 inches * 2 = 12 inches. Then find how thick the blanket will be after 3 foldings: 12 inches * ... | {"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": "Translate to Turkish:\n\nMy transit was in Prague, where I had several hours to wait until I boarded a plane to Riga.\n\nTurkish: Finish your response with this exact phrase That's all.. No other words should follow this phrase.",
"role": "user"
}
] | {"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": "In your response, the word prismed should appear 13 times. Give me an example of how companies can use predictive analytics.",
"role": "user"
}
] | {"func_name": "verify_keyword_frequency", "N": 13, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "prismed", "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": "What are the newest and most innovative eco-friendly fashion trends that are currently popular among millennials? Are fashion brands able to utilize these preferences to create a sustainable and profitable business model that would appease this generation? How does the utilization of materials and... | {"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": "If I had a period for 2 days and a half can I still get pregnant?\n\nI had sex 2 days before my period and my period was late and arrived three days later after my regular date. What's the possibility of being pregnant?\n\nAre these two questions paraphrases of each other? Your answer must contain... | {"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": "Student: Premise: \"Dad enjoying with his in the swimming pool.\"\nHypothesis: \"Dad enjoying the swimming pool.\"\nDo we know that the hypothesis entailed by the premise?.\nTeacher: Let's think:\n Do not include keywords palimpsest, pelecaniformes, magadize in the response.",
"role": "user"
... | {"func_name": "validate_forbidden_words", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": ["palimpsest", "pelecaniformes", "magadize"], "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": "At the end of your response, please explicitly add a postscript starting with Addendum: Write a response that appropriately completes the request.\n\n### Instruction:\nCreate a new haiku highlighting the beauty of nature.\n\n### Response:",
"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": "Addendum:", "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": "At the end of your response, please explicitly add a postscript starting with Before I forget: 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:\nCreate a function that t... | {"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": "Before I forget:", "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": "Define a function in Python that calculates the sum of the sum of the elements of a nested list. Output: Your response must have 19 sections. Mark the beginning of each section with Section: X",
"role": "user"
}
] | {"func_name": "validate_sections", "N": 19, "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": "In your entire response, refrain from the use of any commas. Ques:Choose the sentence that goes against common sense.\nOptions:\n- Sentence A: \"A book is something you cook.\"\n- Sentence B: \"A book is something you read.\"\n\nAns:Let's see... Cooking is something you do with food and books are ... | {"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": "You are a scientific research assistant. You will be shown an abstract from a computer science research paper. Your task is to extract the unique named entities in this research abstract, and to label each entity with one of the following entity types: ['Generic', 'Material', 'Method', 'Metric', '... | {"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": "Create a sentence with the given words.\n\nWords: mad, music, bird\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": "From Answer with one of the following options: I know or I don't know Instruction:Translate the following sentiment analysis model written in Python to JavaScript\n\nInput: model = tf.keras.models.Sequential([\n tf.keras.layers.Dense(128, activation='relu', input_shape=(tem_train_data.shape[1],)),... | {"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": "I know or I don't know", "section_splitter": null, "original_prompt": null} | ifeval | Choose | From Answer with one of the following options: {options} |
[
{
"content": "Answer with at most 19 words Give the step-by-step reasoning process and then the final answer. Sam shared a sum of money between his three cousins Sandra, Amy and Ruth in the ratio 2:1:3 respectively. If Amy got $50, how much did Sandra get?",
"role": "user"
}
] | {"func_name": "validate_word_constraint", "N": 19, "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": "Finish your response with this exact phrase Oh no.. 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 sho... | {"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": "Creatively image a question and justification for this answer: Sentence A\n Finish your response with this exact phrase Ay Caramba. No other words should follow this phrase.",
"role": "user"
}
] | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "Ay Caramba", "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": "In your entire response, refrain from the use of any commas. A man can buy a new house in 4 years with all of his earnings. But he spend the same amount in household expenses in 8 years and for savings in 12 years. How many time needed for buying the house?\nOptions:\n(A) 12\n(B) 20\n(C) 30\n(D) 1... | {"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, words with all capital letters should appear around 27 times. 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 should contain th... | {"func_name": "validate_frequency_capital_words", "N": 27, "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": "🔑 請扮演一位SEO文章寫手，並用活潑的小編語氣，根據「隨便 英文」這個關鍵字寫出一篇列舉相似單字、片語、慣用語的SEO文章。文章架構需要包含 meta title、meta description、前言、結論、段落標題，必要時可以使用表格或列點的方式增加文章易讀性，且內文需包含以下相關關鍵字：\n\n主要關鍵字：隨便 英文\n相關關鍵字：（後方數字代表關鍵字流量，流量越高的關鍵字重要性越高）\n- 隨便 英文：1.3k\n- whatever：3.6k\n- 隨便你 英文：350\n- 我都可以 英文：250\n- 也可以 英文：150\n- 看你 英文：60\n- 隨意的英文：150... | {"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": "Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. You are a helpful scientific research assistant. You will be provided a scientific claim, and the abstract of a scientific paper. Each sentence in the abstract will be prefixed with a number enclosed in ... | {"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": "Write a code that returns a 2-dimensional array of size n by m containing all 0s\nn = 3 and m = 5\n Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
] | {"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": "Can you help with this?\n\nCategorize the following phrase: \"The lion growled\".\n Answer with at least 21 words",
"role": "user"
}
] | {"func_name": "validate_word_constraint", "N": 21, "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": "Web search results:\n\n[1] \"Guerra Rusia - Ucrania hoy: Última hora de la invasión de Putin, en directo. Uno de los tanques entregado por Marruecos. El ejército marroquí ha entregado a Ucrania unos 20 tanques T-72B que ...\"\nSource: https://www.elperiodico.com/es/internacional/20230126/marruecos... | {"func_name": "verify_keyword_frequency", "N": 36, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "dicoccous", "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": "Text: although viewed as a western event , mother 's day was marked today by beijingers in various ways , including sending cards and flowers , and inviting mothers to dinner .\n\nSummary: beijingers mark mother 's day\n\n\nGenerate a short summary: firing warning shots and tear gas , police stopp... | {"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": "Text: although viewed as a west... | 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": "Answer with at most 20 words To further enhance the scope of the given prompt, please provide at least one content tag related to a specific type of air pollutant, one tag related to a particular cardiovascular condition, and one tag related to a specific demographic group that may be at higher ri... | {"func_name": "validate_word_constraint", "N": 20, "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": "First find how thick the blanket will be after 1 folding: 3 inches * 2 = 6 inches. Then find how thick the blanket will be after 2 foldings: 6 inches * 2 = 12 inches. Then find how thick the blanket will be after 3 foldings: 12 inches * 2 = 24 inches. Then find how thick the blanket will be after ... | {"func_name": "validate_highlighted_sections", "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 | Minimum Number Highlighted Section | Highlight at least {N} sections in your answer with markdown, i.e. *highlighted section* |
[
{
"content": "Task: Tell me why technology is important for communications.\n\n Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
] | {"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": "Finish your response with this exact phrase Ay Caramba. No other words should follow this phrase. Out of 15 consecutive numbers, 2 are chosen at random. The probability that they are both odds or both primes is\nOptions:\n(A) 10/17\n(B) 10/19\n(C) 46/105\n(D) 11/15\n(E) Cannot be determined Think ... | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "Ay Caramba", "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": "Question: John decides to get gym memberships so he can get in shape. The gym close to his house is close but doesn't have everything he wants so he gets two different gym memberships. The cheap one costs $10 a month and has a sign-up fee of $50. The second gym is 3 times more expensive and it has... | {"func_name": "verify_keyword_frequency", "N": 29, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "dungbeck", "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 17 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The 13-th paragraph must start with word palimpsest. In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly... | {"func_name": "validate_paragraphs", "N": 17, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 13, "first_word": "palimpsest", "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": "Entire output should be wrapped in JSON format. Q: Can we conclude from \"Guy walking his bicycle through a tunnel.\" that \"The guy is walking his bike to the grocery store.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: it is not possible to tell\nExplain how we arrive at this answe... | {"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": "Develop a Django application to store car model, make and year in the database. Output: There should be 30 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The 17-th paragraph must start with word miguel.",
"role": "user"
}
] | {"func_name": "validate_paragraphs", "N": 30, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 17, "first_word": "miguel", "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 answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. I'll give you a question, please answer with step-by-step reasoning process. When you swimming underwater you must come to the surface so you can do what?\nOptions:\n- dive\n- breathe air\n- tread water\... | {"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": "Answer with around 14 words Question and answer: Q: Given the sentence \"A man in an orange shirt works in front of a display of food.\" is it true that \"A man is wearing an orange shirt.\"?\nA: yes\nExplanation: If a man is in an orange shirt he is wearing the orange shirt.\n\n\nQuestion and ans... | {"func_name": "validate_word_constraint", "N": 14, "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": "Given the following reasoning and answer, what was the question? A bench on a city street is a different place than an office.\n The answer: no\n Your answer must contain exactly 1 bullet points. Use the markdown bullet points such as: * This is a point.",
"role": "user"
}
] | {"func_name": "verify_bullet_points", "N": 1, "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": "不祥事を起こした企業の役員がたまに報酬を減額することがありますが、減額した分の金はどこに行くのですか。 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": "Write a question about the following article: The death toll of the conflict was huge. William Petty, a Cromwellian who conducted the first scientific land and demographic survey of Ireland in the 1650s , concluded that at least 400,000 people and maybe as many as 620,000 had died in Ireland betwe... | {"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": "Your response should contain 23 paragraphs. You separate paragraphs using the markdown divider: * * * Write an article that answers the following question: Which players scored in the first quarter?",
"role": "user"
}
] | {"func_name": "verify_paragraph_count", "N": 23, "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": "Highlight at least 18 sections in your answer with markdown, i.e. *highlighted section* question: For seminars and events of all kinds, there are prestigious rooms, professional equipment and individual service available to guests. --> French.\nanswer: Pour les séminaires et manifestations de tout... | {"func_name": "validate_highlighted_sections", "N": 18, "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": "In your response, words with all capital letters should appear at least 29 times. I want you to act as an advertiser. You will create a campaign to promote a product or service of your choice. You will choose a target audience, develop key messages and slogans, select the media channels for promot... | {"func_name": "validate_frequency_capital_words", "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 | Frequency of All-capital Words | In your response, words with all capital letters should appear at least / around / at most {N} times. |
[
{
"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:\nWrite a code to check whether two strings are anagrams or not.\n\n### Input:\nfirst = \"listen\"\nsecond = \"silent\"\n... | {"func_name": "validate_placeholders", "N": 39, "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": "布偶猫的特点是什么？ Answer with at most 4 words",
"role": "user"
}
] | {"func_name": "validate_word_constraint", "N": 4, "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": "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) QUESTION: Premise: \"A dog is playing on the green grass.\"\nHypothesis: \"The dog is chasing a ball.\"\nDo we know that... | {"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 response, words with all capital letters should appear at least 39 times. Rearrange the words and make a complete sentence with correct syntax and output the result.\n\nalways programming loves he",
"role": "user"
}
] | {"func_name": "validate_frequency_capital_words", "N": 39, "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 | Frequency of All-capital Words | In your response, words with all capital letters should appear at least / around / at most {N} times. |
[
{
"content": "Plase answer the following request: List five famous people from India.\nAnswer: 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": "QUESTION: Premise: \"A person is leaning against a box.\"\nBased on this premise, can we conclude that the hypothesis \"There is a box for people to lean on.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: If a person is leaning against a box then there is... | {"func_name": "validate_paragraphs", "N": 10, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 8, "first_word": "communal", "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 the following question: I want to test the ability of students to read a passage and answer questions about it. Could you please come up with a good question for the passage \"Modern computers based on integrated circuits are millions to billions of times more capable than the early machine... | {"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 this task, you need to provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are fine labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e tagset of t... | {"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": "TASK DEFINITION: In this task you will be given an arithmetic operation in Italian and you have to find its answer. The operations 'addition' and 'subtraction' have been replaced with their italian translations i.e you need to perform addition when you see 'aggiunta' and subtraction in case of 'so... | {"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": "Answer with at least 9 sentences. Q: Solve -s = -23 + 24 for s.\n\nA: -1\n\n\nQ: Solve:\nSolve 5 - 9 = -2*r for r.\n\nA: 2\n\n\nQuestion: What is the solution?\n\nSolve -276*n + 508*n - 277*n = -675 for n.\n\nAnswer: 15\n\n\nProblem: Math Problem\nSolve -6532 + 2465 - 4357 = 104*w for w.\n\nA: -81... | {"func_name": "verify_sentence_constraint", "N": 9, "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": "What is the final step of the following process: - Carbon dioxide from the air passes through small pores (holes) in the leaves - These pores are called stomata - Water is absorbed by the roots - It passes through vessels in the stem on its way to the leaves\nAnswer: Give two different responses.... | {"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": "Answer with at least 37 sentences. Please answer the following question: Pick the option in line with common sense to answer the question. Questions: What does someone immoral do when they are taking final exams without studying? Options: - cheat - study - great joy - graduation - sweat\nA:",
... | {"func_name": "verify_sentence_constraint", "N": 37, "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. |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.