{"id":"W4402683916","doi":"10.18653/v1/2024.acl-srw.35","title":"Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition","year":2024,"lang":"en","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"TRACE (psycholinguistics); Decomposition; Computer science; Distillation; Artificial intelligence; Chemistry; Linguistics; Chromatography; Philosophy; Organic chemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005784216,0.0001534205,0.000161305,0.0001137651,0.0001418342,0.0002515362,0.0002235467,0.00007065592,0.000009910558],"category_scores_gemma":[0.00007580063,0.0001314651,0.0000840416,0.0004798253,0.00003311399,0.0007161676,0.00005239503,0.0001708608,0.00005780479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009815102,"about_ca_system_score_gemma":0.0001248051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006342797,"about_ca_topic_score_gemma":0.000005976024,"domain_scores_codex":[0.9986051,0.0001634321,0.0003976952,0.0004027517,0.0002273927,0.0002036847],"domain_scores_gemma":[0.9992819,0.0001914684,0.0001201385,0.0002145007,0.0001451995,0.00004673603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001737185,0.00003918916,0.000618551,0.0003626829,0.00001469647,0.000003989373,0.00168713,0.003309523,0.01531277,0.9533832,0.0000973152,0.02516919],"study_design_scores_gemma":[0.0001074446,0.0001462651,0.001388,0.001673344,0.00001215637,0.00001319846,0.00004908893,0.8906479,0.0753381,0.003953883,0.02641205,0.0002585404],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04047567,0.0006167945,0.9510194,0.0003363146,0.0007360176,0.0002725369,7.791133e-7,0.0005981296,0.005944333],"genre_scores_gemma":[0.8582827,0.000001447405,0.1395366,0.00001248844,0.0002004477,0.00002218825,0.000006120968,0.00001456671,0.001923467],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9494293,"threshold_uncertainty_score":0.536099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03695600329241108,"score_gpt":0.3365478367036141,"score_spread":0.299591833411203,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}