{"id":"W6891667688","doi":"10.48448/8qn0-4r22","title":"Negated Complementary Commonsense using Large Language Models","year":2023,"lang":"en","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Language model; Language understanding; Commonsense reasoning; Commonsense knowledge; Human language; Natural language","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":[0.002838431,0.0016055,0.0007482828,0.0008604619,0.0007267406,0.002258801,0.001999152,0.002364082,0.01601632],"category_scores_gemma":[0.02164823,0.000482241,0.001318254,0.000488452,0.001426638,0.005229132,0.003945199,0.002935558,0.004562903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008219292,"about_ca_system_score_gemma":0.0009504465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001501376,"about_ca_topic_score_gemma":0.003361957,"domain_scores_codex":[0.9966913,0.001814494,0.0001106908,0.0006932059,0.000573374,0.0001168294],"domain_scores_gemma":[0.9879619,0.009293345,0.0002914184,0.00167198,0.0005211674,0.0002601751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008518517,0.0006012873,0.004437145,0.001476916,0.0002326632,0.001865344,0.002611183,0.107769,0.03289917,0.1253639,0.07426994,0.6476216],"study_design_scores_gemma":[0.00007663536,0.00009016859,0.0004521286,0.00005685278,0.00003423752,0.0005427857,0.0003697892,0.8226435,0.01233395,0.1456451,0.0176971,0.00005776637],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.052661,0.0003364425,0.8999434,0.001770239,0.0002628834,0.0003795401,0.001873779,0.02535718,0.01741557],"genre_scores_gemma":[0.6291347,0.0001466529,0.3493278,0.0008806949,0.0001482219,0.0004064829,0.005710358,0.002369266,0.01187586],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01601632,"threshold_uncertainty_score":0.05357999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1345751029884112,"score_gpt":0.3871135124012318,"score_spread":0.2525384094128206,"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."}}