{"id":"W4389519446","doi":"10.18653/v1/2023.emnlp-main.782","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Benchmark (surveying); Task (project management); Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007353662,0.0001121779,0.0001785133,0.0001190791,0.0003127222,0.00007715516,0.0004108064,0.00005349162,0.000006032371],"category_scores_gemma":[0.00009263967,0.00008632049,0.00004873558,0.000646886,0.00004867613,0.0002354063,0.0004172349,0.0001787113,0.000002498831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002021568,"about_ca_system_score_gemma":0.00005485161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002987284,"about_ca_topic_score_gemma":0.00006570684,"domain_scores_codex":[0.9988136,0.00007978639,0.0002991943,0.0002911914,0.0002545647,0.0002616139],"domain_scores_gemma":[0.9990129,0.0003437673,0.0001385463,0.0003749537,0.00007987173,0.00004992338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004340057,0.00005099968,0.001758655,0.0002987192,0.0001181286,0.0000315689,0.03166248,0.1972971,0.1423224,0.1896369,0.0007595365,0.4360201],"study_design_scores_gemma":[0.0001904288,0.00005044781,0.00008801978,0.00002379168,0.00000463801,0.000008929572,0.0005176989,0.9909874,0.006723443,0.001156381,0.0001510006,0.00009783294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.118122,0.0002394061,0.8776782,0.0003515862,0.0001857263,0.0001287579,3.762298e-7,0.0001829138,0.003111154],"genre_scores_gemma":[0.9724541,0.00002691825,0.02220653,0.00003017725,0.00004160339,0.000009611291,9.505829e-7,0.00001132606,0.005218772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8554716,"threshold_uncertainty_score":0.3520048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03176144178090691,"score_gpt":0.2597585747241698,"score_spread":0.2279971329432629,"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."}}