{"id":"W4388963827","doi":"10.48550/arxiv.2311.13538","title":"AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Guangzhou Municipal Science and Technology Bureau; National Natural Science Foundation of China; Guangdong Science and Technology Department; Institute for Catastrophic Loss Reduction","keywords":"Context (archaeology); Style (visual arts); Computer science; Set (abstract data type); Natural language processing; Code (set theory); Artificial intelligence; Linguistics; Programming language; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001744632,0.001717342,0.0006544973,0.0004246698,0.0004287689,0.001081209,0.002355917,0.00131996,0.01592864],"category_scores_gemma":[0.01640877,0.0004920907,0.0008327449,0.0003704274,0.0006375548,0.00287556,0.003259439,0.002484338,0.006969064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005593966,"about_ca_system_score_gemma":0.000842422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001878619,"about_ca_topic_score_gemma":0.003722821,"domain_scores_codex":[0.9983431,0.0007679732,0.00007675702,0.0005141738,0.0002175802,0.00008041711],"domain_scores_gemma":[0.9952366,0.002917552,0.0001794512,0.001143641,0.0003276214,0.0001951643],"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":[0.001846123,0.0008012157,0.004351737,0.001817043,0.0001445228,0.001352276,0.002822383,0.06213772,0.07671718,0.0145051,0.1277246,0.7057801],"study_design_scores_gemma":[0.0005946155,0.0009232698,0.00217998,0.0001718254,0.0000818347,0.0007910925,0.0009267424,0.7746803,0.06279076,0.03953299,0.1171577,0.0001688174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08404733,0.0009198171,0.7437723,0.0006932742,0.000475937,0.0007054638,0.005813858,0.1536337,0.009938369],"genre_scores_gemma":[0.3979266,0.0003398242,0.5688199,0.0006544766,0.0001168315,0.0008872942,0.01748555,0.004496839,0.009272742],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01592864,"threshold_uncertainty_score":0.05328655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1157023098326443,"score_gpt":0.2207473702077753,"score_spread":0.105045060375131,"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."}}