{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002958602,0.002848246,0.00162019,0.001264901,0.0007439297,0.001856331,0.004439623,0.002787166,0.004868097],"category_scores_gemma":[0.01368111,0.0008604349,0.002165729,0.0009388112,0.001051585,0.00428789,0.002497453,0.005174119,0.003002403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001404105,"about_ca_system_score_gemma":0.002366035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009164261,"about_ca_topic_score_gemma":0.02020781,"domain_scores_codex":[0.9975858,0.0007872398,0.0001553921,0.0009280775,0.0003547412,0.0001886854],"domain_scores_gemma":[0.9948186,0.003274382,0.0001790316,0.0009692042,0.0004982539,0.0002604696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001238898,0.001253688,0.007731648,0.001387811,0.0006353121,0.0005586234,0.0004570266,0.1499704,0.02323288,0.004148452,0.04783831,0.7615469],"study_design_scores_gemma":[0.0002854008,0.0005195089,0.001462697,0.00007806845,0.0001297064,0.0001913078,0.0001525017,0.9698706,0.009998414,0.01011887,0.00711545,0.00007738546],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2643147,0.01110261,0.6139295,0.001723,0.001251169,0.0008845201,0.007359681,0.08771502,0.01171979],"genre_scores_gemma":[0.6246105,0.000770688,0.3360169,0.002111974,0.0002747102,0.0006657112,0.02551076,0.001800397,0.008238343],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009164261,"threshold_uncertainty_score":0.01822186,"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."}}