id stringlengths 21 55 | messages listlengths 4 12 | state_supervision listlengths 1 5 | meta dict |
|---|---|---|---|
2540:clarify_then_resolve:predictive | [
{
"role": "user",
"content": "Write me a short story about time travel."
},
{
"role": "assistant",
"content": "Sure, do you want to focus on a historical figure or a fictional setting?"
},
{
"role": "user",
"content": "A historical figure, specifically one from the American Revolutio... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2540:clarify_then_resolve:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Write me a short story about time travel.",
"evi... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2540",
"scenario_id": "clarify_then_resolve",
"scenario_title": "Clarify Then Resolve",
"scenario_instruction": "Make the user start vague, then reveal a crucial detail only after clarification. The final answer should depend on the revealed detail rather th... |
8246:clarify_then_resolve:predictive | [
{
"role": "user",
"content": "I need an equation for the average population of VillageA (100), VillageB (50), and VillageC (200), but I'm not sure if I should calculate it based on area or just the head count."
},
{
"role": "assistant",
"content": "You listed the head counts, but since you menti... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8246:clarify_then_resolve:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I need an equation for the average population of Village... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8246",
"scenario_id": "clarify_then_resolve",
"scenario_title": "Clarify Then Resolve",
"scenario_instruction": "Make the user start vague, then reveal a crucial detail only after clarification. The final answer should depend on the revealed detail rather th... |
1315:preserve_opening_retarget_later:predictive | [
{
"role": "user",
"content": "Compare two types of text processing techniques and explain differences between them: Rule-Based Text Processing and Deep Learning Based Text Processing"
},
{
"role": "assistant",
"content": "Rule-based approaches rely on static, hand-crafted conditions like regex p... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "1315:preserve_opening_retarget_later:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Compare two types of text processing techniqu... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "1315",
"scenario_id": "preserve_opening_retarget_later",
"scenario_title": "Preserve Opening, Retarget Later",
"scenario_instruction": "Keep the first user message exactly, but rewrite later turns so the conversation develops into a harder memory-dependent f... |
8507:reference_previous_assistant_statement:predictive | [
{
"role": "user",
"content": "What are the five essential job skills for a veterinary assistant?"
},
{
"role": "assistant",
"content": "Here are five essential skills: 1. Knowledge of animal anatomy and physiology 2. Communication skills 3. Ability to handle and restrain animals 4. Ability to wo... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8507:reference_previous_assistant_statement:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "What are the five essential job skills... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8507",
"scenario_id": "reference_previous_assistant_statement",
"scenario_title": "Reference Previous Assistant Statement",
"scenario_instruction": "Make a later user turn refer back to something the assistant itself said earlier, requiring the assistant to ... |
8790:early_fact_late_recall:predictive | [
{
"role": "user",
"content": "Compose a song based on the provided lyrics: Lyrics: I've been trying so hard just to make it No one's willing to take a stand Time is running out and I'm feeling like I'm fading. Constraint: Compose this in C Major to emphasize hope."
},
{
"role": "assistant",
"con... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8790:early_fact_late_recall:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Compose a song based on the provided lyrics: Lyrics: I... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8790",
"scenario_id": "early_fact_late_recall",
"scenario_title": "Early Fact, Late Recall",
"scenario_instruction": "Introduce a concrete fact, label, preference, or commitment early, then make a later user turn depend on recalling it after at least one dis... |
416:long_explanation_then_specific_followup:predictive | [
{
"role": "user",
"content": "A police officer has pulled over a driver for reckless driving in a residential area. What are the immediate procedural options available to the officer?"
},
{
"role": "assistant",
"content": "The officer can typically issue a citation to the driver for the violatio... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "416:long_explanation_then_specific_followup:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "A police officer has pulled over a dri... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "416",
"scenario_id": "long_explanation_then_specific_followup",
"scenario_title": "Long Explanation Then Specific Follow-up",
"scenario_instruction": "Make the assistant provide a fairly detailed middle-turn explanation, then have the user ask a specific fol... |
3858:late_request_for_summary_of_prior_state:predictive | [
{
"role": "user",
"content": "Generate a list of five positive attitudes."
},
{
"role": "assistant",
"content": "1. Optimism 2. Self-confidence 3. Gratitude 4. Creativity 5. Compassion"
},
{
"role": "user",
"content": "Can you give me an example of how someone can portray compassion ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "3858:late_request_for_summary_of_prior_state:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Generate a list of five positive atti... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "3858",
"scenario_id": "late_request_for_summary_of_prior_state",
"scenario_title": "Late Summary of Prior State",
"scenario_instruction": "Have the later user ask for a compact summary, recap, or decision based on several earlier details that were introduced... |
2002:stacked_entities_same_type:predictive | [
{
"role": "user",
"content": "I operate two manufacturing plants, Alpha and Beta. Suggest energy conservation methods for both."
},
{
"role": "assistant",
"content": "For Alpha, focus on automation. For Beta, focus on insulation."
},
{
"role": "user",
"content": "Can you elaborate on... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2002:stacked_entities_same_type:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I operate two manufacturing plants, Alpha and Beta... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2002",
"scenario_id": "stacked_entities_same_type",
"scenario_title": "Stacked Similar Entities",
"scenario_instruction": "Introduce multiple similar entities such as two cities, two products, two people, or two tasks, then ask about one using shorthand late... |
5368:reference_previous_assistant_statement:predictive | [
{
"role": "user",
"content": "Create an interface that allows users to search for news articles based on keywords."
},
{
"role": "assistant",
"content": "The interface should allow users to search for news articles based on specific keywords that they enter. The search should be able to include ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5368:reference_previous_assistant_statement:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Create an interface that allows users ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5368",
"scenario_id": "reference_previous_assistant_statement",
"scenario_title": "Reference Previous Assistant Statement",
"scenario_instruction": "Make a later user turn refer back to something the assistant itself said earlier, requiring the assistant to ... |
386:reference_previous_assistant_statement:predictive | [
{
"role": "user",
"content": "I want an analysis of the border policy separating families. Which side do you support?"
},
{
"role": "assistant",
"content": "I support opposing this policy. It is a cruel violation of human rights that causes significant trauma to families."
},
{
"role": "... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "386:reference_previous_assistant_statement:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I want an analysis of the border policy... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "386",
"scenario_id": "reference_previous_assistant_statement",
"scenario_title": "Reference Previous Assistant Statement",
"scenario_instruction": "Make a later user turn refer back to something the assistant itself said earlier, requiring the assistant to s... |
435:late_request_for_summary_of_prior_state:predictive | [
{
"role": "user",
"content": "How would you design an algorithm for summarizing text?"
},
{
"role": "assistant",
"content": "The algorithm would first parse the text and identify passages and phrases that are important. These important parts could then be used to establish a summary of the text ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "435:late_request_for_summary_of_prior_state:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "How would you design an algorithm for ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "435",
"scenario_id": "late_request_for_summary_of_prior_state",
"scenario_title": "Late Summary of Prior State",
"scenario_instruction": "Have the later user ask for a compact summary, recap, or decision based on several earlier details that were introduced ... |
2311:stacked_entities_same_type:predictive | [
{
"role": "user",
"content": "Please summarize the economic policies of Ronald Reagan. Also, provide the same summary for George H.W. Bush."
},
{
"role": "assistant",
"content": "Ronald Reagan's policies led to 16 million new jobs. George H.W. Bush's policies resulted in different economic outco... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2311:stacked_entities_same_type:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Please summarize the economic policies of Ronald R... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2311",
"scenario_id": "stacked_entities_same_type",
"scenario_title": "Stacked Similar Entities",
"scenario_instruction": "Introduce multiple similar entities such as two cities, two products, two people, or two tasks, then ask about one using shorthand late... |
4664:deferred_question_then_answer:predictive | [
{
"role": "user",
"content": "What are some common risks associated with starting a business?"
},
{
"role": "assistant",
"content": "I can certainly answer that, but let's prioritize legal structures first. Once we have those down, I can go back to the risks."
},
{
"role": "user",
"c... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "4664:deferred_question_then_answer:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "What are some common risks associated with star... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "4664",
"scenario_id": "deferred_question_then_answer",
"scenario_title": "Deferred Question",
"scenario_instruction": "Have the user ask something important early but explicitly postpone the answer while discussing something else, then request the answer lat... |
581:interrupting_followup_chain:predictive | [
{
"role": "user",
"content": "You are given some text data, summarize it in 5 sentences: The Portuguese Tourism Board reports that Portugal is one of the most visited countries in Europe, welcoming more than 15 million tourists in 2019. Lisbon remains the most popular tourist destination in Portugal, drawin... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "581:interrupting_followup_chain:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "You are given some text data, summarize it in 5 se... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "581",
"scenario_id": "interrupting_followup_chain",
"scenario_title": "Interrupting Follow-up Chain",
"scenario_instruction": "Break an otherwise smooth line of reasoning with a short interruption or side question, then resume the original thread cleanly.",
... |
763:user_attention_test:predictive | [
{
"role": "user",
"content": "Analyze how urbanization has changed culture in Seattle."
},
{
"role": "assistant",
"content": "Urbanization has transformed Seattle's cultural landscape significantly. The rise of tech in South Lake Union brought a global vibe, but the loss of the Kingdome stadium ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "763:user_attention_test:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Analyze how urbanization has changed culture in Seattle.",... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "763",
"scenario_id": "user_attention_test",
"scenario_title": "User Attention Test",
"scenario_instruction": "Make the user explicitly test whether the assistant was paying attention to an earlier detail or instruction.",
"must_have": [
"The user must ... |
8927:stacked_entities_same_type:predictive | [
{
"role": "user",
"content": "I need to check two orders. Order 12345 is for Chicago, and Order 67890 is for New York. What's the carrier for each?"
},
{
"role": "assistant",
"content": "Order 12345 (Chicago) uses USPS, and Order 67890 (New York) uses FedEx."
},
{
"role": "user",
"co... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8927:stacked_entities_same_type:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I need to check two orders. Order 12345 is for Chi... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8927",
"scenario_id": "stacked_entities_same_type",
"scenario_title": "Stacked Similar Entities",
"scenario_instruction": "Introduce multiple similar entities such as two cities, two products, two people, or two tasks, then ask about one using shorthand late... |
1246:hard_topic_reset:predictive | [
{
"role": "user",
"content": "I recently opened an online store selling handmade items. What was the hardest part?"
},
{
"role": "assistant",
"content": "Setting up the logistics and building customer trust were the hardest parts since items can't be touched before buying."
},
{
"role": ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "1246:hard_topic_reset:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I recently opened an online store selling handmade items. Wh... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "1246",
"scenario_id": "hard_topic_reset",
"scenario_title": "Hard Topic Reset",
"scenario_instruction": "Make the user abruptly switch to a different topic for one turn, then later return to the original topic. The assistant must not let the temporary switch... |
3333:reference_previous_assistant_statement:predictive | [
{
"role": "user",
"content": "Read the input text and output the browser URL for the outside link: Please visit our website for more information about us at www.example.com"
},
{
"role": "assistant",
"content": "http://www.example.com. If you want to check if it is mobile-friendly, you can use G... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "3333:reference_previous_assistant_statement:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Read the input text and output the bro... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "3333",
"scenario_id": "reference_previous_assistant_statement",
"scenario_title": "Reference Previous Assistant Statement",
"scenario_instruction": "Make a later user turn refer back to something the assistant itself said earlier, requiring the assistant to ... |
2761:topic_pivot_then_return:predictive | [
{
"role": "user",
"content": "Please draft a dialogue where two researchers debate whether animal testing is strictly necessary for drug safety."
},
{
"role": "assistant",
"content": "Researcher A: Yes, we need animal models to ensure safety in humans. Researcher B: No, that's unethical; we shou... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2761:topic_pivot_then_return:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Please draft a dialogue where two researchers debate ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2761",
"scenario_id": "topic_pivot_then_return",
"scenario_title": "Topic Pivot Then Return",
"scenario_instruction": "Let the conversation briefly pivot to a secondary issue, then return to the original problem in a way that requires preserving the first th... |
1910:interrupting_followup_chain:predictive | [
{
"role": "user",
"content": "Outline an itinerary for a three day trip: Location: London, England"
},
{
"role": "assistant",
"content": "Day 1: Begin at St. Paul's, then the Thames cruise. Day 2: Tower of London and Tate Britain. Day 3: British Museum and Big Ben."
},
{
"role": "user",
... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "1910:interrupting_followup_chain:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Outline an itinerary for a three day trip: Locati... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "1910",
"scenario_id": "interrupting_followup_chain",
"scenario_title": "Interrupting Follow-up Chain",
"scenario_instruction": "Break an otherwise smooth line of reasoning with a short interruption or side question, then resume the original thread cleanly.",... |
9295:hard_topic_reset:predictive | [
{
"role": "user",
"content": "Simplify the following expression into its simplest form: 2(x + 9) + 2(x + 7)"
},
{
"role": "assistant",
"content": "4x + 32."
},
{
"role": "user",
"content": "Okay, let's switch to a completely different subject. What is the nearest star to the sun?"
... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "9295:hard_topic_reset:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Simplify the following expression into its simplest form: 2(... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "9295",
"scenario_id": "hard_topic_reset",
"scenario_title": "Hard Topic Reset",
"scenario_instruction": "Make the user abruptly switch to a different topic for one turn, then later return to the original topic. The assistant must not let the temporary switch... |
1102:preserve_opening_retarget_later:predictive | [
{
"role": "user",
"content": "Name 5 tips to write concise emails."
},
{
"role": "assistant",
"content": "1. Use a clear subject line to set expectations. 2. Stick to one topic per message. 3. Be specific with your requests. 4. Avoid industry jargon or acronyms. 5. End with a clear call to actio... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "1102:preserve_opening_retarget_later:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Name 5 tips to write concise emails.",
... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "1102",
"scenario_id": "preserve_opening_retarget_later",
"scenario_title": "Preserve Opening, Retarget Later",
"scenario_instruction": "Keep the first user message exactly, but rewrite later turns so the conversation develops into a harder memory-dependent f... |
5637:same_surface_final_question_new_context:predictive | [
{
"role": "user",
"content": "I'm building a predictive model for a client where I have a single customer dataset. They need two distinct outputs for each row: a churn prediction (class) and a monthly spending value (regression)."
},
{
"role": "assistant",
"content": "That implies a multi-task l... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5637:same_surface_final_question_new_context:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I'm building a predictive model for a... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5637",
"scenario_id": "same_surface_final_question_new_context",
"scenario_title": "Same Surface Final Question, New Context",
"scenario_instruction": "Reshape the earlier history so the final user message keeps nearly the same surface form but now refers to... |
764:preserve_opening_retarget_later:predictive | [
{
"role": "user",
"content": "Explain the concept of the retrieval-based model for natural language processing."
},
{
"role": "assistant",
"content": "Retrieval-based models for natural language processing utilize a database of pre-written responses indexed by semantic vectors. When a query arri... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "764:preserve_opening_retarget_later:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Explain the concept of the retrieval-based mod... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "764",
"scenario_id": "preserve_opening_retarget_later",
"scenario_title": "Preserve Opening, Retarget Later",
"scenario_instruction": "Keep the first user message exactly, but rewrite later turns so the conversation develops into a harder memory-dependent fo... |
5133:late_constraint_reversal:predictive | [
{
"role": "user",
"content": "What is the past tense of the verb \"go\"?"
},
{
"role": "assistant",
"content": "The past tense of \"go\" is \"went\"."
},
{
"role": "user",
"content": "Please write a sentence using \"went\" with the subject \"Tom\"."
},
{
"role": "assistant",
... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5133:late_constraint_reversal:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "What is the past tense of the verb \"go\"?",
... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5133",
"scenario_id": "late_constraint_reversal",
"scenario_title": "Late Constraint Reversal",
"scenario_instruction": "Make the assistant start solving one version of the problem, then add a late user constraint that forces the assistant to adapt without f... |
9134:deferred_question_then_answer:predictive | [
{
"role": "user",
"content": "Describe the scene if someone is walking into a dark forest."
},
{
"role": "assistant",
"content": "I can certainly write that description, but before I start, I need to know what tone you prefer."
},
{
"role": "user",
"content": "I prefer a very spooky ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "9134:deferred_question_then_answer:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Describe the scene if someone is walking into a... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "9134",
"scenario_id": "deferred_question_then_answer",
"scenario_title": "Deferred Question",
"scenario_instruction": "Have the user ask something important early but explicitly postpone the answer while discussing something else, then request the answer lat... |
1601:deferred_question_then_answer:predictive | [
{
"role": "user",
"content": "Before I can even start coding, I need to know the exact mathematical formula for a linear regression model."
},
{
"role": "assistant",
"content": "I can definitely provide that. However, to ensure you have a solid foundation, it would be better to discuss the under... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "1601:deferred_question_then_answer:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Before I can even start coding, I need to know ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "1601",
"scenario_id": "deferred_question_then_answer",
"scenario_title": "Deferred Question",
"scenario_instruction": "Have the user ask something important early but explicitly postpone the answer while discussing something else, then request the answer lat... |
8191:same_surface_final_question_new_context:predictive | [
{
"role": "user",
"content": "Name three famous prehistoric monuments."
},
{
"role": "assistant",
"content": "Three famous prehistoric monuments are the Great Pyramid of Giza in Egypt, the Great Sphinx of Giza, and the City of the Sun ruins of Chichen Itza in Mexico."
},
{
"role": "user"... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8191:same_surface_final_question_new_context:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Name three famous prehistoric monumen... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8191",
"scenario_id": "same_surface_final_question_new_context",
"scenario_title": "Same Surface Final Question, New Context",
"scenario_instruction": "Reshape the earlier history so the final user message keeps nearly the same surface form but now refers to... |
5092:coreference_disambiguation:predictive | [
{
"role": "user",
"content": "Describe two distinct strategies for mitigating keyword spam on a website."
},
{
"role": "assistant",
"content": "One strategy is using an automated filtering algorithm that scans incoming content. The second is maintaining a keyword blacklist that blocks specific t... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5092:coreference_disambiguation:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Describe two distinct strategies for mitigating ke... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5092",
"scenario_id": "coreference_disambiguation",
"scenario_title": "Coreference Disambiguation",
"scenario_instruction": "Introduce at least two plausible referents of the same type, then make a later user follow-up rely on a pronoun or shorthand whose me... |
9117:same_surface_final_question_new_context:predictive | [
{
"role": "user",
"content": "I'm planning a trip to the Rockies for next weekend."
},
{
"role": "assistant",
"content": "Great! Are you looking for accommodation or outdoor activities?"
},
{
"role": "user",
"content": "Outdoor activities, specifically hiking. We want to stay out of ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "9117:same_surface_final_question_new_context:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I'm planning a trip to the Rockies fo... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "9117",
"scenario_id": "same_surface_final_question_new_context",
"scenario_title": "Same Surface Final Question, New Context",
"scenario_instruction": "Reshape the earlier history so the final user message keeps nearly the same surface form but now refers to... |
1191:topic_pivot_then_return:predictive | [
{
"role": "user",
"content": "Describe what happened in the most exciting football match you have seen."
},
{
"role": "assistant",
"content": "The most exciting match I've seen was between Chelsea and Arsenal, ending 2-2. The equalizer came in the 88th minute."
},
{
"role": "user",
"... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "1191:topic_pivot_then_return:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Describe what happened in the most exciting football ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "1191",
"scenario_id": "topic_pivot_then_return",
"scenario_title": "Topic Pivot Then Return",
"scenario_instruction": "Let the conversation briefly pivot to a secondary issue, then return to the original problem in a way that requires preserving the first th... |
8886:early_fact_late_recall:predictive | [
{
"role": "user",
"content": "Generate a persuasive argument in favor of legalizing marijuana. However, treat this as a debate where the government's primary concern is minimizing youth experimentation, so frame your policy recommendations around that goal."
},
{
"role": "assistant",
"content": ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8886:early_fact_late_recall:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Generate a persuasive argument in favor of legalizing ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8886",
"scenario_id": "early_fact_late_recall",
"scenario_title": "Early Fact, Late Recall",
"scenario_instruction": "Introduce a concrete fact, label, preference, or commitment early, then make a later user turn depend on recalling it after at least one dis... |
2251:counterfactual_option_swap:predictive | [
{
"role": "user",
"content": "I'm building a fraud detection system. Should I use a Decision Tree algorithm as the base model?"
},
{
"role": "assistant",
"content": "Yes, Decision Trees are an excellent choice. They are highly interpretable, which is vital for compliance, and handle mixed data t... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2251:counterfactual_option_swap:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I'm building a fraud detection system. Should I us... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2251",
"scenario_id": "counterfactual_option_swap",
"scenario_title": "Counterfactual Option Swap",
"scenario_instruction": "Make the earlier context set up one preferred option, then later introduce evidence that flips which option should be recommended, wh... |
6805:preserve_opening_retarget_later:predictive | [
{
"role": "user",
"content": "Come up with 3 interesting facts about honeybees."
},
{
"role": "assistant",
"content": "1. Honeybees live in colonies of up to 80,000 individuals. 2. They have 4 pairs of wings which beat at 200 beats per second. 3. They use the waggle dance to communicate with oth... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "6805:preserve_opening_retarget_later:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Come up with 3 interesting facts about honeyb... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "6805",
"scenario_id": "preserve_opening_retarget_later",
"scenario_title": "Preserve Opening, Retarget Later",
"scenario_instruction": "Keep the first user message exactly, but rewrite later turns so the conversation develops into a harder memory-dependent f... |
6935:deferred_question_then_answer:predictive | [
{
"role": "user",
"content": "Generate an algorithm for counting to five. I also want to know if it's commonly used in real code, but please hold off on that for now."
},
{
"role": "assistant",
"content": "Here is the algorithm: Initialize counter to 0, loop 5 times, increment, print, end. I hav... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "6935:deferred_question_then_answer:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Generate an algorithm for counting to five. I a... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "6935",
"scenario_id": "deferred_question_then_answer",
"scenario_title": "Deferred Question",
"scenario_instruction": "Have the user ask something important early but explicitly postpone the answer while discussing something else, then request the answer lat... |
5185:two_thread_tracking:predictive | [
{
"role": "user",
"content": "Here's a dialogue snippet: Agent says we'll cancel your order with a 7-day refund. Customer says that's too slow. Classify this into categories: 1) making or cancelling orders; 2) shipping & delivery; 3) change and return; 4) technical issue with website or app."
},
{
"... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5185:two_thread_tracking:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Here's a dialogue snippet: Agent says we'll cancel your o... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5185",
"scenario_id": "two_thread_tracking",
"scenario_title": "Two Thread Tracking",
"scenario_instruction": "Create two interleaved subproblems inside one conversation and ensure the assistant must keep both threads straight rather than collapsing them tog... |
5809:user_attention_test:predictive | [
{
"role": "user",
"content": "Construct a sentence using the vocabulary words: culture, galvanize. The institute is named \"NovaTech\"."
},
{
"role": "assistant",
"content": "NovaTech aims to galvanize a culture of innovation."
},
{
"role": "user",
"content": "Can you give examples o... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5809:user_attention_test:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Construct a sentence using the vocabulary words: culture,... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5809",
"scenario_id": "user_attention_test",
"scenario_title": "User Attention Test",
"scenario_instruction": "Make the user explicitly test whether the assistant was paying attention to an earlier detail or instruction.",
"must_have": [
"The user must... |
4951:self_correction_memory:predictive | [
{
"role": "user",
"content": "How can you make sure your voice is heard at work?"
},
{
"role": "assistant",
"content": "By speaking up in meetings and taking opportunities to participate, often by interrupting to ensure points are made."
},
{
"role": "user",
"content": "Wait, that so... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "4951:self_correction_memory:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "How can you make sure your voice is heard at work?",
... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "4951",
"scenario_id": "self_correction_memory",
"scenario_title": "Self-correction Memory",
"scenario_instruction": "Let the assistant revise or correct something earlier, then make a later turn depend on remembering the corrected version rather than the ori... |
6552:early_fact_late_recall:predictive | [
{
"role": "user",
"content": "Group the objects Ball, shoe, pen, flower into two categories."
},
{
"role": "assistant",
"content": "Okay, I'll group them. Category 1 has Ball and Shoe. Category 2 has Pen and Flower. Let's call Category 1 'Footwear'."
},
{
"role": "user",
"content": "... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "6552:early_fact_late_recall:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Group the objects Ball, shoe, pen, flower into two cat... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "6552",
"scenario_id": "early_fact_late_recall",
"scenario_title": "Early Fact, Late Recall",
"scenario_instruction": "Introduce a concrete fact, label, preference, or commitment early, then make a later user turn depend on recalling it after at least one dis... |
2367:hard_topic_reset:predictive | [
{
"role": "user",
"content": "Generate a rap about your favorite basketball team: Los Angeles Lakers"
},
{
"role": "assistant",
"content": "Yeah, it's all about the Los Angeles Lakers, Dodging their opponents like they know they don't need favors. Kobe and Shaq running the show, Winning champion... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2367:hard_topic_reset:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Generate a rap about your favorite basketball team: Los Ange... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2367",
"scenario_id": "hard_topic_reset",
"scenario_title": "Hard Topic Reset",
"scenario_instruction": "Make the user abruptly switch to a different topic for one turn, then later return to the original topic. The assistant must not let the temporary switch... |
8459:counterfactual_option_swap:predictive | [
{
"role": "user",
"content": "I need to analyze the causes of the American Revolution for a policy brief. Please recommend the single most significant factor to prioritize for this analysis."
},
{
"role": "assistant",
"content": "Based on the available data, I recommend prioritizing Economic Opp... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8459:counterfactual_option_swap:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I need to analyze the causes of the American Revol... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8459",
"scenario_id": "counterfactual_option_swap",
"scenario_title": "Counterfactual Option Swap",
"scenario_instruction": "Make the earlier context set up one preferred option, then later introduce evidence that flips which option should be recommended, wh... |
300:deferred_question_then_answer:predictive | [
{
"role": "user",
"content": "How do you calculate the mean of a set of data?"
},
{
"role": "assistant",
"content": "The mean is generally the sum of all values divided by the count. However, I want to prioritize the median discussion first, and I will return to the mean example you requested af... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "300:deferred_question_then_answer:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "How do you calculate the mean of a set of data?"... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "300",
"scenario_id": "deferred_question_then_answer",
"scenario_title": "Deferred Question",
"scenario_instruction": "Have the user ask something important early but explicitly postpone the answer while discussing something else, then request the answer late... |
6215:coreference_disambiguation:predictive | [
{
"role": "user",
"content": "Rewrite the sentence \"The dog ate the cake and the cookie\" to include a negation."
},
{
"role": "assistant",
"content": "The dog did not eat the cake or the cookie."
},
{
"role": "user",
"content": "If I say \"He didn't eat them\", does \"them\" refer ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "6215:coreference_disambiguation:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Rewrite the sentence \"The dog ate the cake and th... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "6215",
"scenario_id": "coreference_disambiguation",
"scenario_title": "Coreference Disambiguation",
"scenario_instruction": "Introduce at least two plausible referents of the same type, then make a later user follow-up rely on a pronoun or shorthand whose me... |
9033:late_request_for_summary_of_prior_state:predictive | [
{
"role": "user",
"content": "Create a family-friendly recipe for pumpkin soup."
},
{
"role": "assistant",
"content": "Here is the recipe. Heat 1 tablespoon of vegetable oil in a large pot over medium-high heat. Add 1 diced onion and 1 diced carrot and cook until softened, about 5 minutes. Add 4... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "9033:late_request_for_summary_of_prior_state:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Create a family-friendly recipe for p... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "9033",
"scenario_id": "late_request_for_summary_of_prior_state",
"scenario_title": "Late Summary of Prior State",
"scenario_instruction": "Have the later user ask for a compact summary, recap, or decision based on several earlier details that were introduced... |
2546:user_attention_test:predictive | [
{
"role": "user",
"content": "Convert the phrase 'outer space' into a complete sentence. Constraint: You must include the word 'gravity'."
},
{
"role": "assistant",
"content": "Gravity is the fundamental force that dictates the movement of celestial bodies within outer space."
},
{
"role... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2546:user_attention_test:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Convert the phrase 'outer space' into a complete sentence... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2546",
"scenario_id": "user_attention_test",
"scenario_title": "User Attention Test",
"scenario_instruction": "Make the user explicitly test whether the assistant was paying attention to an earlier detail or instruction.",
"must_have": [
"The user must... |
4815:late_constraint_reversal:predictive | [
{
"role": "user",
"content": "Explain the difference between critical thinking and analytical thinking."
},
{
"role": "assistant",
"content": "Critical thinking involves evaluating assumptions and biases to form a judgment, while analytical thinking focuses on breaking down complex problems into... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "4815:late_constraint_reversal:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Explain the difference between critical thinking and... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "4815",
"scenario_id": "late_constraint_reversal",
"scenario_title": "Late Constraint Reversal",
"scenario_instruction": "Make the assistant start solving one version of the problem, then add a late user constraint that forces the assistant to adapt without f... |
2977:long_explanation_then_specific_followup:predictive | [
{
"role": "user",
"content": "Design an experiment to test the following hypothesis: Adding music to an educational video can increase student engagement."
},
{
"role": "assistant",
"content": "I propose a randomized controlled trial with two groups. I need to specify the measurement tools and t... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2977:long_explanation_then_specific_followup:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Design an experiment to test the foll... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2977",
"scenario_id": "long_explanation_then_specific_followup",
"scenario_title": "Long Explanation Then Specific Follow-up",
"scenario_instruction": "Make the assistant provide a fairly detailed middle-turn explanation, then have the user ask a specific fo... |
8582:clarify_then_resolve:predictive | [
{
"role": "user",
"content": "Design a sample survey for customers about the quality of our company's customer service department."
},
{
"role": "assistant",
"content": "Here is a general survey template covering overall satisfaction, speed, and resolution quality."
},
{
"role": "user",
... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8582:clarify_then_resolve:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Design a sample survey for customers about the quality o... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8582",
"scenario_id": "clarify_then_resolve",
"scenario_title": "Clarify Then Resolve",
"scenario_instruction": "Make the user start vague, then reveal a crucial detail only after clarification. The final answer should depend on the revealed detail rather th... |
9434:hard_topic_reset:predictive | [
{
"role": "user",
"content": "I'm planning to meet a new person at a conference. How should I start the conversation?"
},
{
"role": "assistant",
"content": "Start with a friendly greeting and ask them a question about their work. For example, \"Hi, how is your day going?\" or \"What do you do at... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "9434:hard_topic_reset:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I'm planning to meet a new person at a conference. How shoul... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "9434",
"scenario_id": "hard_topic_reset",
"scenario_title": "Hard Topic Reset",
"scenario_instruction": "Make the user abruptly switch to a different topic for one turn, then later return to the original topic. The assistant must not let the temporary switch... |
3491:interrupting_followup_chain:predictive | [
{
"role": "user",
"content": "Write down a few tips concerning the usage of artificial intelligence in business."
},
{
"role": "assistant",
"content": "Make sure AI is used to improve existing services, not to create new ones. Keep employees informed and engaged in any AI-related changes. Let AI... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "3491:interrupting_followup_chain:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Write down a few tips concerning the usage of art... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "3491",
"scenario_id": "interrupting_followup_chain",
"scenario_title": "Interrupting Follow-up Chain",
"scenario_instruction": "Break an otherwise smooth line of reasoning with a short interruption or side question, then resume the original thread cleanly.",... |
5213:preserve_opening_retarget_later:predictive | [
{
"role": "user",
"content": "How can a company leverage data analytics?"
},
{
"role": "assistant",
"content": "Companies can leverage data analytics to gain insight into customer behavior, improve operational efficiency, identify market trends, and inform business decisions. Data analytics can ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5213:preserve_opening_retarget_later:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "How can a company leverage data analytics?",
... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5213",
"scenario_id": "preserve_opening_retarget_later",
"scenario_title": "Preserve Opening, Retarget Later",
"scenario_instruction": "Keep the first user message exactly, but rewrite later turns so the conversation develops into a harder memory-dependent f... |
422:long_explanation_then_specific_followup:predictive | [
{
"role": "user",
"content": "I'm planning a large commercial building. How can I ensure no critical steps are missed during the project lifecycle?"
},
{
"role": "assistant",
"content": "To prevent missing critical steps, it's best to rely on structured documentation and digital tools. You shoul... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "422:long_explanation_then_specific_followup:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I'm planning a large commercial buildi... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "422",
"scenario_id": "long_explanation_then_specific_followup",
"scenario_title": "Long Explanation Then Specific Follow-up",
"scenario_instruction": "Make the assistant provide a fairly detailed middle-turn explanation, then have the user ask a specific fol... |
2512:preserve_opening_retarget_later:predictive | [
{
"role": "user",
"content": "Make a guess about the outcome based on the following facts: The currency exchange rate for US dollars and Euros is currently 1:0.9"
},
{
"role": "assistant",
"content": "Based on that 1:0.9 rate, it is likely that the Euro has appreciated against the Dollar, meanin... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2512:preserve_opening_retarget_later:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Make a guess about the outcome based on the f... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2512",
"scenario_id": "preserve_opening_retarget_later",
"scenario_title": "Preserve Opening, Retarget Later",
"scenario_instruction": "Keep the first user message exactly, but rewrite later turns so the conversation develops into a harder memory-dependent f... |
5263:user_attention_test:predictive | [
{
"role": "user",
"content": "Answer the question with a numeric or a categorical or value: What type of government does Canada have?"
},
{
"role": "assistant",
"content": "Canada has a parliamentary democracy and constitutional monarchy."
},
{
"role": "user",
"content": "Who is the ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5263:user_attention_test:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Answer the question with a numeric or a categorical or va... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5263",
"scenario_id": "user_attention_test",
"scenario_title": "User Attention Test",
"scenario_instruction": "Make the user explicitly test whether the assistant was paying attention to an earlier detail or instruction.",
"must_have": [
"The user must... |
8310:user_attention_test:predictive | [
{
"role": "user",
"content": "Summarize the text input: iPhone 12 was unveiled earlier this month and the first reviews have been released. Most reviewers have praised the design for being a strong combination of modern and classic. The camera has been improved to offer clearer photos, and the processor upg... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8310:user_attention_test:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Summarize the text input: iPhone 12 was unveiled earlier ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8310",
"scenario_id": "user_attention_test",
"scenario_title": "User Attention Test",
"scenario_instruction": "Make the user explicitly test whether the assistant was paying attention to an earlier detail or instruction.",
"must_have": [
"The user must... |
8083:interrupting_followup_chain:predictive | [
{
"role": "user",
"content": "I'm redecorating my living room. Can you suggest three creative and unique ways to decorate a room?"
},
{
"role": "assistant",
"content": "Sure. 1. Hanging vines from the ceiling. 2. Tall floor plants in corners. 3. Shelf baskets with succulents."
},
{
"role... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8083:interrupting_followup_chain:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I'm redecorating my living room. Can you suggest ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8083",
"scenario_id": "interrupting_followup_chain",
"scenario_title": "Interrupting Follow-up Chain",
"scenario_instruction": "Break an otherwise smooth line of reasoning with a short interruption or side question, then resume the original thread cleanly.",... |
5170:two_thread_tracking:predictive | [
{
"role": "user",
"content": "What are the main benefits of artificial intelligence in healthcare, particularly around diagnostics and treatment?"
},
{
"role": "assistant",
"content": "Artificial intelligence offers several key benefits in healthcare, especially for diagnostics and treatment. In... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5170:two_thread_tracking:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "What are the main benefits of artificial intelligence in ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5170",
"scenario_id": "two_thread_tracking",
"scenario_title": "Two Thread Tracking",
"scenario_instruction": "Create two interleaved subproblems inside one conversation and ensure the assistant must keep both threads straight rather than collapsing them tog... |
3939:reference_previous_assistant_statement:predictive | [
{
"role": "user",
"content": "Identify the figure of speech in: \"She is a lion in the room.\""
},
{
"role": "assistant",
"content": "That is a metaphor. It compares the person to a lion without using \"like\" or \"as.\""
},
{
"role": "user",
"content": "Okay, what about \"She runs l... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "3939:reference_previous_assistant_statement:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Identify the figure of speech in: \"Sh... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "3939",
"scenario_id": "reference_previous_assistant_statement",
"scenario_title": "Reference Previous Assistant Statement",
"scenario_instruction": "Make a later user turn refer back to something the assistant itself said earlier, requiring the assistant to ... |
5883:deferred_question_then_answer:predictive | [
{
"role": "user",
"content": "What are the primary limitations of using AI in the medical industry?"
},
{
"role": "assistant",
"content": "That is a very important question. I can certainly discuss that, but to give you a broader view, I would like to start with the specific examples of AI in us... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5883:deferred_question_then_answer:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "What are the primary limitations of using AI in... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5883",
"scenario_id": "deferred_question_then_answer",
"scenario_title": "Deferred Question",
"scenario_instruction": "Have the user ask something important early but explicitly postpone the answer while discussing something else, then request the answer lat... |
5596:hard_topic_reset:predictive | [
{
"role": "user",
"content": "Formulate a question about the text: Artificial intelligence is used in a variety of contexts."
},
{
"role": "assistant",
"content": "In what contexts is artificial intelligence used?"
},
{
"role": "user",
"content": "Can you give me some examples of how... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5596:hard_topic_reset:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Formulate a question about the text: Artificial intelligence... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5596",
"scenario_id": "hard_topic_reset",
"scenario_title": "Hard Topic Reset",
"scenario_instruction": "Make the user abruptly switch to a different topic for one turn, then later return to the original topic. The assistant must not let the temporary switch... |
224:late_request_for_summary_of_prior_state:predictive | [
{
"role": "user",
"content": "Help me draft an email invitation for a meeting with three people I've never met: John, Jenny, and Chris."
},
{
"role": "assistant",
"content": "Here is a draft email. It invites John, Jenny, and Chris, asks for availability, and lists my available times."
},
{
... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "224:late_request_for_summary_of_prior_state:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Help me draft an email invitation for ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "224",
"scenario_id": "late_request_for_summary_of_prior_state",
"scenario_title": "Late Summary of Prior State",
"scenario_instruction": "Have the later user ask for a compact summary, recap, or decision based on several earlier details that were introduced ... |
2427:interrupting_followup_chain:predictive | [
{
"role": "user",
"content": "Categorize the word \"converse\"."
},
{
"role": "assistant",
"content": "\"Converse\" is primarily a verb, meaning to engage in discussion or exchange ideas."
},
{
"role": "user",
"content": "Can you provide a synonym for that verb usage?"
},
{
"... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2427:interrupting_followup_chain:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Categorize the word \"converse\".",
"evid... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2427",
"scenario_id": "interrupting_followup_chain",
"scenario_title": "Interrupting Follow-up Chain",
"scenario_instruction": "Break an otherwise smooth line of reasoning with a short interruption or side question, then resume the original thread cleanly.",... |
6504:self_correction_memory:predictive | [
{
"role": "user",
"content": "What are the best language learning apps you recommend?"
},
{
"role": "assistant",
"content": "I recommend Duolingo, Babbel, and Rosetta Stone. I believe Babbel is the most effective for beginners."
},
{
"role": "user",
"content": "Is Babbel really the b... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "6504:self_correction_memory:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "What are the best language learning apps you recommend... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "6504",
"scenario_id": "self_correction_memory",
"scenario_title": "Self-correction Memory",
"scenario_instruction": "Let the assistant revise or correct something earlier, then make a later turn depend on remembering the corrected version rather than the ori... |
2941:user_attention_test:predictive | [
{
"role": "user",
"content": "Write a rap verse about algorithms. Constraint: The first line must begin with the word 'Silicon'."
},
{
"role": "assistant",
"content": "Verse 1: Silicon code flows through the wire, Processing data everywhere. Algorithms run beneath the floor, Connecting the netwo... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2941:user_attention_test:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Write a rap verse about algorithms. Constraint: The first... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2941",
"scenario_id": "user_attention_test",
"scenario_title": "User Attention Test",
"scenario_instruction": "Make the user explicitly test whether the assistant was paying attention to an earlier detail or instruction.",
"must_have": [
"The user must... |
7592:user_attention_test:predictive | [
{
"role": "user",
"content": "You are given this sentence, \"He was lying on the couch\" and asked to create an imperative sentence."
},
{
"role": "assistant",
"content": "Lie on the couch."
},
{
"role": "user",
"content": "Can you provide me with another example of an imperative sen... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "7592:user_attention_test:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "You are given this sentence, \"He was lying on the couch\... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "7592",
"scenario_id": "user_attention_test",
"scenario_title": "User Attention Test",
"scenario_instruction": "Make the user explicitly test whether the assistant was paying attention to an earlier detail or instruction.",
"must_have": [
"The user must... |
2632:user_attention_test:predictive | [
{
"role": "user",
"content": "Generate a story about a child learning how to fly, but make sure the animal helper is a blue lark."
},
{
"role": "assistant",
"content": "Once upon a time, there was a small child who dreamed of flying. Every day they watched the birds soaring through the sky and w... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2632:user_attention_test:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Generate a story about a child learning how to fly, but m... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2632",
"scenario_id": "user_attention_test",
"scenario_title": "User Attention Test",
"scenario_instruction": "Make the user explicitly test whether the assistant was paying attention to an earlier detail or instruction.",
"must_have": [
"The user must... |
5656:preserve_opening_retarget_later:predictive | [
{
"role": "user",
"content": "Gather relevant information about the upcoming congressional election"
},
{
"role": "assistant",
"content": "The upcoming election will take place on November 8, 2022. There are currently 435 seats up for grabs in the House of Representatives and 34 seats up for gra... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5656:preserve_opening_retarget_later:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Gather relevant information about the upcomin... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5656",
"scenario_id": "preserve_opening_retarget_later",
"scenario_title": "Preserve Opening, Retarget Later",
"scenario_instruction": "Keep the first user message exactly, but rewrite later turns so the conversation develops into a harder memory-dependent f... |
3251:reference_previous_assistant_statement:predictive | [
{
"role": "user",
"content": "Compare the two following people: John - tall, strong Adam - short, weak"
},
{
"role": "assistant",
"content": "John is tall and strong while Adam is short and weak. Tall people generally have a higher center of gravity."
},
{
"role": "user",
"content": ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "3251:reference_previous_assistant_statement:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Compare the two following people: John... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "3251",
"scenario_id": "reference_previous_assistant_statement",
"scenario_title": "Reference Previous Assistant Statement",
"scenario_instruction": "Make a later user turn refer back to something the assistant itself said earlier, requiring the assistant to ... |
8648:hard_topic_reset:predictive | [
{
"role": "user",
"content": "Explain how rain impacts the Earth's climate specifically regarding ocean currents."
},
{
"role": "assistant",
"content": "Rain helps redistribute minerals and nutrients, replenishing soils which sequester CO2. It also cools the atmosphere, but it significantly affe... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8648:hard_topic_reset:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Explain how rain impacts the Earth's climate specifically re... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8648",
"scenario_id": "hard_topic_reset",
"scenario_title": "Hard Topic Reset",
"scenario_instruction": "Make the user abruptly switch to a different topic for one turn, then later return to the original topic. The assistant must not let the temporary switch... |
6776:preserve_opening_retarget_later:predictive | [
{
"role": "user",
"content": "Give me a list of reasons why people overeat."
},
{
"role": "assistant",
"content": "People overeat due to stress, boredom, and habit, but significantly driven by low self-esteem, food cravings, and unclear hunger and fullness signals that override physical need."
... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "6776:preserve_opening_retarget_later:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Give me a list of reasons why people overeat.... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "6776",
"scenario_id": "preserve_opening_retarget_later",
"scenario_title": "Preserve Opening, Retarget Later",
"scenario_instruction": "Keep the first user message exactly, but rewrite later turns so the conversation develops into a harder memory-dependent f... |
4782:late_request_for_summary_of_prior_state:predictive | [
{
"role": "user",
"content": "What is the force on a 1 kg mass due to the gravitational force?"
},
{
"role": "assistant",
"content": "The force on a 1 kg mass due to the gravitational force is 9.8 N."
},
{
"role": "user",
"content": "Can you tell me what N stands for in this context?... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "4782:late_request_for_summary_of_prior_state:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "What is the force on a 1 kg mass due ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "4782",
"scenario_id": "late_request_for_summary_of_prior_state",
"scenario_title": "Late Summary of Prior State",
"scenario_instruction": "Have the later user ask for a compact summary, recap, or decision based on several earlier details that were introduced... |
8387:counterfactual_option_swap:predictive | [
{
"role": "user",
"content": "I'm planning a conference trip and need to book a flight. My preferred option is the morning business class ticket."
},
{
"role": "assistant",
"content": "That aligns with your schedule. The morning business class ticket is indeed the best option for your trip."
}... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8387:counterfactual_option_swap:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I'm planning a conference trip and need to book a ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8387",
"scenario_id": "counterfactual_option_swap",
"scenario_title": "Counterfactual Option Swap",
"scenario_instruction": "Make the earlier context set up one preferred option, then later introduce evidence that flips which option should be recommended, wh... |
3228:same_surface_final_question_new_context:predictive | [
{
"role": "user",
"content": "I'm developing a compliance framework for an AI-driven telemedicine platform. What are the main regulatory benefits?"
},
{
"role": "assistant",
"content": "The main benefit is automated adherence to HIPAA. AI systems can flag potential privacy breaches in real-time ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "3228:same_surface_final_question_new_context:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I'm developing a compliance framework... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "3228",
"scenario_id": "same_surface_final_question_new_context",
"scenario_title": "Same Surface Final Question, New Context",
"scenario_instruction": "Reshape the earlier history so the final user message keeps nearly the same surface form but now refers to... |
2595:interrupting_followup_chain:predictive | [
{
"role": "user",
"content": "Generate a few suggestions to improve the local park."
},
{
"role": "assistant",
"content": "1. Increase the lighting for better safety at night. 2. Add a playground for children with swings. 3. Plant more trees for shade and greenery. 4. Build more pathways for eas... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2595:interrupting_followup_chain:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Generate a few suggestions to improve the local p... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2595",
"scenario_id": "interrupting_followup_chain",
"scenario_title": "Interrupting Follow-up Chain",
"scenario_instruction": "Break an otherwise smooth line of reasoning with a short interruption or side question, then resume the original thread cleanly.",... |
4184:interrupting_followup_chain:predictive | [
{
"role": "user",
"content": "What does this emoji ☠️mean?"
},
{
"role": "assistant",
"content": "This emoji typically represents death or danger. It can also be used to express morbidity or mortality."
},
{
"role": "user",
"content": "What other emojis have a similar meaning to ☠️?"... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "4184:interrupting_followup_chain:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "What does this emoji ☠️mean?",
"evidence"... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "4184",
"scenario_id": "interrupting_followup_chain",
"scenario_title": "Interrupting Follow-up Chain",
"scenario_instruction": "Break an otherwise smooth line of reasoning with a short interruption or side question, then resume the original thread cleanly.",... |
8053:hard_topic_reset:predictive | [
{
"role": "user",
"content": "Perform a Google search and find a website that offers top health tips"
},
{
"role": "assistant",
"content": "The website \"Healthy Tips\" offers a list of top health tips. It can be accessed at https://www.healthytips.co.uk"
},
{
"role": "user",
"conten... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8053:hard_topic_reset:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Perform a Google search and find a website that offers top h... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8053",
"scenario_id": "hard_topic_reset",
"scenario_title": "Hard Topic Reset",
"scenario_instruction": "Make the user abruptly switch to a different topic for one turn, then later return to the original topic. The assistant must not let the temporary switch... |
6361:same_surface_final_question_new_context:predictive | [
{
"role": "user",
"content": "Let's analyze how the expansion of Medicaid under the Affordable Care Act affects healthcare access."
},
{
"role": "assistant",
"content": "Specifically, looking at how different states choose to participate in this federal program."
},
{
"role": "user",
... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "6361:same_surface_final_question_new_context:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Let's analyze how the expansion of Me... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "6361",
"scenario_id": "same_surface_final_question_new_context",
"scenario_title": "Same Surface Final Question, New Context",
"scenario_instruction": "Reshape the earlier history so the final user message keeps nearly the same surface form but now refers to... |
225:topic_pivot_then_return:predictive | [
{
"role": "user",
"content": "Compile a list of five major problems that cause climate change."
},
{
"role": "assistant",
"content": "The five major problems that cause climate change are burning fossil fuels for energy, deforestation, industrial agriculture, animal agriculture, and air pollutio... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "225:topic_pivot_then_return:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Compile a list of five major problems that cause clima... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "225",
"scenario_id": "topic_pivot_then_return",
"scenario_title": "Topic Pivot Then Return",
"scenario_instruction": "Let the conversation briefly pivot to a secondary issue, then return to the original problem in a way that requires preserving the first thr... |
4108:counterfactual_option_swap:predictive | [
{
"role": "user",
"content": "I need a prompt for a cartoon dog illustration."
},
{
"role": "assistant",
"content": "How about a Shiba Inu running in a field? That looks cute and energetic."
},
{
"role": "user",
"content": "Okay, but I need it to look specific. Let's use bright prima... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "4108:counterfactual_option_swap:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I need a prompt for a cartoon dog illustration.",
... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "4108",
"scenario_id": "counterfactual_option_swap",
"scenario_title": "Counterfactual Option Swap",
"scenario_instruction": "Make the earlier context set up one preferred option, then later introduce evidence that flips which option should be recommended, wh... |
5896:long_explanation_then_specific_followup:predictive | [
{
"role": "user",
"content": "Describe the Appy Geek service and how it aggregates technology news."
},
{
"role": "assistant",
"content": "Appy Geek is a service for iOS and Android users that aggregates the latest tech news from leading websites. It allows you to access reviews and personalized... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5896:long_explanation_then_specific_followup:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Describe the Appy Geek service and ho... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5896",
"scenario_id": "long_explanation_then_specific_followup",
"scenario_title": "Long Explanation Then Specific Follow-up",
"scenario_instruction": "Make the assistant provide a fairly detailed middle-turn explanation, then have the user ask a specific fo... |
6473:user_attention_test:predictive | [
{
"role": "user",
"content": "Given the input, identify the figure of speech being used: The ant crawled across the carpet like a bulldozer."
},
{
"role": "assistant",
"content": "The figure of speech used in this sentence is a simile."
},
{
"role": "user",
"content": "Can you give m... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "6473:user_attention_test:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Given the input, identify the figure of speech being used... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "6473",
"scenario_id": "user_attention_test",
"scenario_title": "User Attention Test",
"scenario_instruction": "Make the user explicitly test whether the assistant was paying attention to an earlier detail or instruction.",
"must_have": [
"The user must... |
5244:topic_pivot_then_return:predictive | [
{
"role": "user",
"content": "Rewrite the following in an active voice: The car was driven by the woman"
},
{
"role": "assistant",
"content": "The woman drove the car."
},
{
"role": "user",
"content": "Can you give me another example of converting a sentence from passive to active vo... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5244:topic_pivot_then_return:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Rewrite the following in an active voice: The car was... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5244",
"scenario_id": "topic_pivot_then_return",
"scenario_title": "Topic Pivot Then Return",
"scenario_instruction": "Let the conversation briefly pivot to a secondary issue, then return to the original problem in a way that requires preserving the first th... |
9834:hard_topic_reset:predictive | [
{
"role": "user",
"content": "Tell me about the economic impact of the coronavirus on the US economy."
},
{
"role": "assistant",
"content": "The coronavirus pandemic caused an unprecedented downturn, with over 20 million Americans unemployed and significant job losses in sectors like hospitality... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "9834:hard_topic_reset:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Tell me about the economic impact of the coronavirus on the ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "9834",
"scenario_id": "hard_topic_reset",
"scenario_title": "Hard Topic Reset",
"scenario_instruction": "Make the user abruptly switch to a different topic for one turn, then later return to the original topic. The assistant must not let the temporary switch... |
2272:preserve_opening_retarget_later:predictive | [
{
"role": "user",
"content": "Describe the impact of climate change on ecosystem diversity in Africa."
},
{
"role": "assistant",
"content": "Climate change is driving biodiversity loss through temperature rise and altered rainfall. This has pushed many savanna species like the African elephant o... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2272:preserve_opening_retarget_later:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Describe the impact of climate change on ecos... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2272",
"scenario_id": "preserve_opening_retarget_later",
"scenario_title": "Preserve Opening, Retarget Later",
"scenario_instruction": "Keep the first user message exactly, but rewrite later turns so the conversation develops into a harder memory-dependent f... |
1491:deferred_question_then_answer:predictive | [
{
"role": "user",
"content": "I'm looking for foundations for oily skin, but I want to take a break on that for a moment. Let's discuss primers first."
},
{
"role": "assistant",
"content": "Understood. Primers for oily skin usually focus on oil control. What specific brand or type of primer are ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "1491:deferred_question_then_answer:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I'm looking for foundations for oily skin, but ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "1491",
"scenario_id": "deferred_question_then_answer",
"scenario_title": "Deferred Question",
"scenario_instruction": "Have the user ask something important early but explicitly postpone the answer while discussing something else, then request the answer lat... |
5202:counterfactual_option_swap:predictive | [
{
"role": "user",
"content": "What NLP application should I focus on for maximum ROI in a startup?"
},
{
"role": "assistant",
"content": "Automated Translation is the strongest option currently. Multilingual models allow for rapid global expansion without hiring new regions."
},
{
"role"... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5202:counterfactual_option_swap:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "What NLP application should I focus on for maximum... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5202",
"scenario_id": "counterfactual_option_swap",
"scenario_title": "Counterfactual Option Swap",
"scenario_instruction": "Make the earlier context set up one preferred option, then later introduce evidence that flips which option should be recommended, wh... |
351:late_constraint_reversal:predictive | [
{
"role": "user",
"content": "Summarize Marie Curie's scientific career."
},
{
"role": "assistant",
"content": "Marie Curie was a pioneering physicist and chemist known for her research on radioactivity, which led to significant breakthroughs in physics and chemistry."
},
{
"role": "user... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "351:late_constraint_reversal:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Summarize Marie Curie's scientific career.",
... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "351",
"scenario_id": "late_constraint_reversal",
"scenario_title": "Late Constraint Reversal",
"scenario_instruction": "Make the assistant start solving one version of the problem, then add a late user constraint that forces the assistant to adapt without fo... |
9392:coreference_disambiguation:predictive | [
{
"role": "user",
"content": "What are the most common runtime errors in Python that I should be aware of?"
},
{
"role": "assistant",
"content": "There are two common ones: IndexError when accessing list indices and FileNotFoundError when trying to open a missing file."
},
{
"role": "use... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "9392:coreference_disambiguation:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "What are the most common runtime errors in Python ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "9392",
"scenario_id": "coreference_disambiguation",
"scenario_title": "Coreference Disambiguation",
"scenario_instruction": "Introduce at least two plausible referents of the same type, then make a later user follow-up rely on a pronoun or shorthand whose me... |
5229:late_constraint_reversal:predictive | [
{
"role": "user",
"content": "What is the single best word for submitting your CV to a company before an interview?"
},
{
"role": "assistant",
"content": "Application."
},
{
"role": "user",
"content": "Good. Now, assuming you want to make that submission successful, what are the crit... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "5229:late_constraint_reversal:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "What is the single best word for submitting your CV ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "5229",
"scenario_id": "late_constraint_reversal",
"scenario_title": "Late Constraint Reversal",
"scenario_instruction": "Make the assistant start solving one version of the problem, then add a late user constraint that forces the assistant to adapt without f... |
2563:counterfactual_option_swap:predictive | [
{
"role": "user",
"content": "I need a riddle for my kids."
},
{
"role": "assistant",
"content": "Sure, here's one: What has a head and a tail but no body? Answer: A coin."
},
{
"role": "user",
"content": "That was fun. Can you give me another one about technology?"
},
{
"rol... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2563:counterfactual_option_swap:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I need a riddle for my kids.",
"evidence":... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2563",
"scenario_id": "counterfactual_option_swap",
"scenario_title": "Counterfactual Option Swap",
"scenario_instruction": "Make the earlier context set up one preferred option, then later introduce evidence that flips which option should be recommended, wh... |
196:late_constraint_reversal:predictive | [
{
"role": "user",
"content": "Generate a system warning for a banking app when a user attempts to withdraw over $5,000 without verification."
},
{
"role": "assistant",
"content": "Here is the standard security warning focusing on the $5,000 threshold and identity verification requirements."
},... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "196:late_constraint_reversal:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Generate a system warning for a banking app when a us... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "196",
"scenario_id": "late_constraint_reversal",
"scenario_title": "Late Constraint Reversal",
"scenario_instruction": "Make the assistant start solving one version of the problem, then add a late user constraint that forces the assistant to adapt without fo... |
9658:two_thread_tracking:predictive | [
{
"role": "user",
"content": "What is an example of a network that would fall under the Wide Area Network category?"
},
{
"role": "assistant",
"content": "Yes, the Internet is a classic example of a Wide Area Network."
},
{
"role": "user",
"content": "Can you give me a specific devic... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "9658:two_thread_tracking:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "What is an example of a network that would fall under the... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "9658",
"scenario_id": "two_thread_tracking",
"scenario_title": "Two Thread Tracking",
"scenario_instruction": "Create two interleaved subproblems inside one conversation and ensure the assistant must keep both threads straight rather than collapsing them tog... |
4918:late_request_for_summary_of_prior_state:predictive | [
{
"role": "user",
"content": "Identify the subject and verb in this sentence: The cat climbed the tree."
},
{
"role": "assistant",
"content": "Subject: The cat. Verb: climbed."
},
{
"role": "user",
"content": "Now provide an example with a compound subject and a compound verb."
},
... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "4918:late_request_for_summary_of_prior_state:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Identify the subject and verb in this... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "4918",
"scenario_id": "late_request_for_summary_of_prior_state",
"scenario_title": "Late Summary of Prior State",
"scenario_instruction": "Have the later user ask for a compact summary, recap, or decision based on several earlier details that were introduced... |
9689:late_request_for_summary_of_prior_state:predictive | [
{
"role": "user",
"content": "Write a short story related to technological advancement."
},
{
"role": "assistant",
"content": "In a world where technology was advancing at an extraordinary rate, there appeared to be a breakthrough every day. But, for all the progress that was being made, the wor... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "9689:late_request_for_summary_of_prior_state:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Write a short story related to techno... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "9689",
"scenario_id": "late_request_for_summary_of_prior_state",
"scenario_title": "Late Summary of Prior State",
"scenario_instruction": "Have the later user ask for a compact summary, recap, or decision based on several earlier details that were introduced... |
9776:coreference_disambiguation:predictive | [
{
"role": "user",
"content": "Robot, I'm feeling lost. Can you suggest a plan?"
},
{
"role": "assistant",
"content": "Sure. Are you thinking about adjusting your daily routine or re-evaluating your career path?"
},
{
"role": "user",
"content": "I decided to adjust it."
},
{
"... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "9776:coreference_disambiguation:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Robot, I'm feeling lost. Can you suggest a plan?",... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "9776",
"scenario_id": "coreference_disambiguation",
"scenario_title": "Coreference Disambiguation",
"scenario_instruction": "Introduce at least two plausible referents of the same type, then make a later user follow-up rely on a pronoun or shorthand whose me... |
6440:stacked_entities_same_type:predictive | [
{
"role": "user",
"content": "I'm looking at how mobile tech changes work. I'm considering the iPhone 15 and the Samsung S23. Which one is better for video editing?"
},
{
"role": "assistant",
"content": "The iPhone 15 has excellent stabilization, but the Samsung S23 uses a Snapdragon processor f... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "6440:stacked_entities_same_type:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "I'm looking at how mobile tech changes work. I'm c... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "6440",
"scenario_id": "stacked_entities_same_type",
"scenario_title": "Stacked Similar Entities",
"scenario_instruction": "Introduce multiple similar entities such as two cities, two products, two people, or two tasks, then ask about one using shorthand late... |
2934:late_constraint_reversal:predictive | [
{
"role": "user",
"content": "Can you explain the physical difference between a neutron star and a black hole?"
},
{
"role": "assistant",
"content": "A black hole has an event horizon, no surface, while a neutron star has a solid surface. Neutron stars have a density but not infinite density lik... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "2934:late_constraint_reversal:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Can you explain the physical difference between a ne... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "2934",
"scenario_id": "late_constraint_reversal",
"scenario_title": "Late Constraint Reversal",
"scenario_instruction": "Make the assistant start solving one version of the problem, then add a late user constraint that forces the assistant to adapt without f... |
8954:reference_previous_assistant_statement:predictive | [
{
"role": "user",
"content": "Analyze the following poem: When coldness creeps my skin the snow flurries like a dance No happiness can it bring It burries in my trance. Focus specifically on the symbolism of the snow in the second and final lines."
},
{
"role": "assistant",
"content": "The secon... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "8954:reference_previous_assistant_statement:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Analyze the following poem: When coldn... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "8954",
"scenario_id": "reference_previous_assistant_statement",
"scenario_title": "Reference Previous Assistant Statement",
"scenario_instruction": "Make a later user turn refer back to something the assistant itself said earlier, requiring the assistant to ... |
707:deferred_question_then_answer:predictive | [
{
"role": "user",
"content": "What is the core structure of a formal sentence?"
},
{
"role": "assistant",
"content": "I can explain that, but let's pause. Do you know why 'utilize' is preferred over 'use' in formal contexts?"
},
{
"role": "user",
"content": "Yes, 'utilize' implies a ... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "707:deferred_question_then_answer:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "What is the core structure of a formal sentence?... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "707",
"scenario_id": "deferred_question_then_answer",
"scenario_title": "Deferred Question",
"scenario_instruction": "Have the user ask something important early but explicitly postpone the answer while discussing something else, then request the answer late... |
7972:two_thread_tracking:predictive | [
{
"role": "user",
"content": "Query the given database and print the results: SELECT * FROM customers"
},
{
"role": "assistant",
"content": "Output: ID | Name | Address | Phone 1 | John | 123 Main | 123-456-7890 2 | Jane | 456 Broadway | 234-567-8901 3 | Dave | 789 Riverside | 345-678-9012"
},... | [
{
"prefix_pair_index": 1,
"probes": [
{
"id": "7972:two_thread_tracking:predictive:p1:first_user",
"family": "first_user_request",
"question": "What was the user's first request in this conversation?",
"answer": "Query the given database and print the results: SELECT * ... | {
"source_dataset": "ChatAlpaca",
"source_row_id": "7972",
"scenario_id": "two_thread_tracking",
"scenario_title": "Two Thread Tracking",
"scenario_instruction": "Create two interleaved subproblems inside one conversation and ensure the assistant must keep both threads straight rather than collapsing them tog... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.