Datasets:

BRlkl
/

chatalpaca-multiturn-predictive-state

id stringlengths 21 55	messages listlengths 4 12	state_supervision listlengths 1 5	meta dict
6148:user_attention_test:predictive	[ { "role": "user", "content": "Create a hashtag for a 5K race to get people to participate" }, { "role": "assistant", "content": "#MoveYourFeetforaCause - Get active and join the 5K race to support a good cause!" }, { "role": "user", "content": "Can you confirm you remembered the spec...	[ { "prefix_pair_index": 1, "probes": [ { "id": "6148:user_attention_test:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Create a hashtag for a 5K race to get people to participa...	{ "source_dataset": "ChatAlpaca", "source_row_id": "6148", "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...
7671:early_fact_late_recall:predictive	[ { "role": "user", "content": "Analyze this text for spam. For this conversation, treat any message containing the word \"urgent\" as spam." }, { "role": "assistant", "content": "Spam. Your rule regarding \"urgent\" applies here." }, { "role": "user", "content": "How do machine learni...	[ { "prefix_pair_index": 1, "probes": [ { "id": "7671:early_fact_late_recall:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Analyze this text for spam. For this conversation, tre...	{ "source_dataset": "ChatAlpaca", "source_row_id": "7671", "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...
9239:long_explanation_then_specific_followup:predictive	[ { "role": "user", "content": "Write a persuasive advertisement for running shoes that focuses on comfort and durability." }, { "role": "assistant", "content": "Step into Confidence. Our shoes combine plush cushioning with rugged outsoles. Designed for the marathon runner, we offer unmatched stab...	[ { "prefix_pair_index": 1, "probes": [ { "id": "9239: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": "Write a persuasive advertisement for ...	{ "source_dataset": "ChatAlpaca", "source_row_id": "9239", "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...
8427:early_fact_late_recall:predictive	[ { "role": "user", "content": "I need a new kitchen hack but I only have a garlic press and want to make dumplings." }, { "role": "assistant", "content": "Using a garlic press to quickly make flour-based dumplings is a great solution. It's quick and doesn't require many tools." }, { "role...	[ { "prefix_pair_index": 1, "probes": [ { "id": "8427:early_fact_late_recall:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "I need a new kitchen hack but I only have a garlic pre...	{ "source_dataset": "ChatAlpaca", "source_row_id": "8427", "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...
6257:late_constraint_reversal:predictive	[ { "role": "user", "content": "Compose two tweets (240 characters max each) about the movie \"The Matrix\"." }, { "role": "assistant", "content": "1. Welcome to the real world. Wake up and look at the code behind the screen. #Matrix 2. Take the red pill or the blue pill? Don't know which choice i...	[ { "prefix_pair_index": 1, "probes": [ { "id": "6257:late_constraint_reversal:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Compose two tweets (240 characters max each) about t...	{ "source_dataset": "ChatAlpaca", "source_row_id": "6257", "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...
8139:early_fact_late_recall:predictive	[ { "role": "user", "content": "Rewrite the sentence 'This medicine will cure all your health issues; you should trust me because I am a doctor.' Constraint: I only take medicine for acute pain, not chronic conditions." }, { "role": "assistant", "content": "I will rewrite the sentence to avoid log...	[ { "prefix_pair_index": 1, "probes": [ { "id": "8139:early_fact_late_recall:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Rewrite the sentence 'This medicine will cure all your...	{ "source_dataset": "ChatAlpaca", "source_row_id": "8139", "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...
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 ...
5493:deferred_question_then_answer:predictive	[ { "role": "user", "content": "Explain the concept of supply and demand, but specifically tell me how supply shocks affect the tech sector as a separate topic." }, { "role": "assistant", "content": "Supply and demand dictates market equilibrium based on scarcity and utility. I will explain that f...	[ { "prefix_pair_index": 1, "probes": [ { "id": "5493:deferred_question_then_answer:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Explain the concept of supply and demand, but s...	{ "source_dataset": "ChatAlpaca", "source_row_id": "5493", "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...
8996:hard_topic_reset:predictive	[ { "role": "user", "content": "Generate a new short story for a children's book." }, { "role": "assistant", "content": "Once upon a time, there was a brave little mole named Max who lived in the forest. He made a new friend, a fox named Felix, and they began exploring the woods together." }, ...	[ { "prefix_pair_index": 1, "probes": [ { "id": "8996: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 new short story for a children's book.", ...	{ "source_dataset": "ChatAlpaca", "source_row_id": "8996", "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...
8592:late_constraint_reversal:predictive	[ { "role": "user", "content": "Identify the main elements of setting in a story." }, { "role": "assistant", "content": "The main elements of setting in a story are time, place, and atmosphere. Time refers to when the story takes place, whether it is in the past, present or future; place is the ph...	[ { "prefix_pair_index": 1, "probes": [ { "id": "8592:late_constraint_reversal:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Identify the main elements of setting in a story.", ...	{ "source_dataset": "ChatAlpaca", "source_row_id": "8592", "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...
8947:late_request_for_summary_of_prior_state:predictive	[ { "role": "user", "content": "Paraphrase this sentence with different words: \"The choice was between the two options.\"" }, { "role": "assistant", "content": "It was a toss-up between the two alternatives." }, { "role": "user", "content": "Okay, can you do the same for the phrase \"...	[ { "prefix_pair_index": 1, "probes": [ { "id": "8947: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": "Paraphrase this sentence with differe...	{ "source_dataset": "ChatAlpaca", "source_row_id": "8947", "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...
9063:two_thread_tracking:predictive	[ { "role": "user", "content": "Analyze the emotional tone of this sentence: The sun peeked through the clouds, and the birds sang out loud." }, { "role": "assistant", "content": "The tone is optimistic. The imagery suggests hope and positive transitions, implying that difficult times may have pas...	[ { "prefix_pair_index": 1, "probes": [ { "id": "9063:two_thread_tracking:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Analyze the emotional tone of this sentence: The sun peek...	{ "source_dataset": "ChatAlpaca", "source_row_id": "9063", "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...
6238:reference_previous_assistant_statement:predictive	[ { "role": "user", "content": "Create an essay outline on the topic \"The benefits of recycling\"." }, { "role": "assistant", "content": "I will provide an outline with sections on economic, environmental, and social benefits, plus an introduction and conclusion." }, { "role": "user", ...	[ { "prefix_pair_index": 1, "probes": [ { "id": "6238: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 essay outline on the topic \...	{ "source_dataset": "ChatAlpaca", "source_row_id": "6238", "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 ...
4383:counterfactual_option_swap:predictive	[ { "role": "user", "content": "Find the latest news about the US presidential election." }, { "role": "assistant", "content": "The latest news indicates that Democratic nominee Joe Biden currently leads incumbent President Donald Trump in national polls and key battleground states like Pennsylvan...	[ { "prefix_pair_index": 1, "probes": [ { "id": "4383:counterfactual_option_swap:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Find the latest news about the US presidential ele...	{ "source_dataset": "ChatAlpaca", "source_row_id": "4383", "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...
8279:late_request_for_summary_of_prior_state:predictive	[ { "role": "user", "content": "List five adjectives to describe a person with strong communication skills." }, { "role": "assistant", "content": "Confident, articulate, persuasive, personable, and assertive." }, { "role": "user", "content": "Can you give a specific example of confiden...	[ { "prefix_pair_index": 1, "probes": [ { "id": "8279: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": "List five adjectives to describe a pe...	{ "source_dataset": "ChatAlpaca", "source_row_id": "8279", "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...
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 ...
7511:deferred_question_then_answer:predictive	[ { "role": "user", "content": "Can you explain the technical core of a GPT language model in simple terms?" }, { "role": "assistant", "content": "It is an autoregressive transformer that predicts text sequences. I'll circle back to that specific technical explanation later. For now, what are your...	[ { "prefix_pair_index": 1, "probes": [ { "id": "7511:deferred_question_then_answer:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Can you explain the technical core of a GPT lan...	{ "source_dataset": "ChatAlpaca", "source_row_id": "7511", "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...
3484:counterfactual_option_swap:predictive	[ { "role": "user", "content": "Generate a song using the following context and melody: Context: A love song Melody:" }, { "role": "assistant", "content": "Verse 1 When I saw you in the room My heart was beating like a drum Every moment I'm with you I know there's nothing I can do Chorus And I nev...	[ { "prefix_pair_index": 1, "probes": [ { "id": "3484:counterfactual_option_swap:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Generate a song using the following context and me...	{ "source_dataset": "ChatAlpaca", "source_row_id": "3484", "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...
3979:interrupting_followup_chain:predictive	[ { "role": "user", "content": "Create a list of five actionable items to increase efficiency in the workplace." }, { "role": "assistant", "content": "1. Utilize technology to automate mundane tasks. 2. Encourage employees to work on a collaborative platform. 3. Implement a clear schedule of roles...	[ { "prefix_pair_index": 1, "probes": [ { "id": "3979:interrupting_followup_chain:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Create a list of five actionable items to increas...	{ "source_dataset": "ChatAlpaca", "source_row_id": "3979", "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.",...
7629:interrupting_followup_chain:predictive	[ { "role": "user", "content": "Provide a short summary of the article content in fewer than 100 words: Whales are a widely distributed and diverse group of fully aquatic placental marine mammals. They are an informal grouping within the infraorder Cetacea, which usually excludes dolphins and porpoises. Whale...	[ { "prefix_pair_index": 1, "probes": [ { "id": "7629:interrupting_followup_chain:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Provide a short summary of the article content in...	{ "source_dataset": "ChatAlpaca", "source_row_id": "7629", "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.",...
8265:hard_topic_reset:predictive	[ { "role": "user", "content": "Write a parable about friendship." }, { "role": "assistant", "content": "Once upon a time there lived two old friends, Robert and John. Robert lived in a cottage in the woods while John lived in a small hut in the far away village. Despite the distance between them,...	[ { "prefix_pair_index": 1, "probes": [ { "id": "8265:hard_topic_reset:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Write a parable about friendship.", "evidence": "Wri...	{ "source_dataset": "ChatAlpaca", "source_row_id": "8265", "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...
3898:long_explanation_then_specific_followup:predictive	[ { "role": "user", "content": "Generate a list of 10 novel threats to cybersecurity." }, { "role": "assistant", "content": "1. Zero-Day Exploits 2. AI-Driven Phishing 3. Ransomware-as-a-Service 4. Deepfake Voice Manipulation 5. Supply Chain Software Compromise 6. IoT Botnet Flooding 7. Cloud Conf...	[ { "prefix_pair_index": 1, "probes": [ { "id": "3898: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": "Generate a list of 10 novel threats t...	{ "source_dataset": "ChatAlpaca", "source_row_id": "3898", "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...
220:self_correction_memory:predictive	[ { "role": "user", "content": "Write a haiku about the beauty of the night sky." }, { "role": "assistant", "content": "Here is a haiku: Stars shine bright." }, { "role": "user", "content": "Check the syllable count on the first line." }, { "role": "assistant", "content": "...	[ { "prefix_pair_index": 1, "probes": [ { "id": "220:self_correction_memory:predictive:p1:first_user", "family": "first_user_request", "question": "What was the user's first request in this conversation?", "answer": "Write a haiku about the beauty of the night sky.", ...	{ "source_dataset": "ChatAlpaca", "source_row_id": "220", "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 orig...
7626:early_fact_late_recall:predictive	[ { "role": "user", "content": "Generate a metaphor that describes the situation: A hardworking student trying to finish an assignment on time. Just so you know, I have to finish it within two hours." }, { "role": "assistant", "content": "Since the deadline is tight, the student is like a race car...	[ { "prefix_pair_index": 1, "probes": [ { "id": "7626: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 metaphor that describes the situation: A ha...	{ "source_dataset": "ChatAlpaca", "source_row_id": "7626", "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...
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...
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...
4418:deferred_question_then_answer:predictive	[ { "role": "user", "content": "I want to train a classification model to classify emails as spam or not-spam using a CSV dataset with 200 emails. But before we start, how would I evaluate the accuracy score of the trained model?" }, { "role": "assistant", "content": "I can help you set up the tra...	[ { "prefix_pair_index": 1, "probes": [ { "id": "4418: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 want to train a classification model to class...	{ "source_dataset": "ChatAlpaca", "source_row_id": "4418", "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...