Datasets:

BRlkl
/

chatalpaca-multiturn-predictive-state2

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...