{"id":"W3207553988","doi":"10.18653/v1/2022.acl-long.225","title":"Generated Knowledge Prompting for Commonsense Reasoning","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","topic":"Topic Modeling","field":"Computer Science","cited_by":176,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Naval Information Warfare Center Pacific; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Allen Institute for Artificial Intelligence","keywords":"Commonsense reasoning; Commonsense knowledge; Cognitive science; Computer science; Computational linguistics; Artificial intelligence; Natural language processing; Linguistics; Epistemology; Philosophy; Psychology; Knowledge representation and reasoning","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002541355,0.0001848675,0.000307317,0.00009564617,0.001285028,0.00009326965,0.001440453,0.00007160343,0.00000128422],"category_scores_gemma":[0.01422684,0.000160454,0.0002999713,0.0005417204,0.00004745418,0.0000740282,0.0008893099,0.0002656453,4.736991e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003884869,"about_ca_system_score_gemma":0.0002405379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002346016,"about_ca_topic_score_gemma":0.000004302318,"domain_scores_codex":[0.9977403,0.00005909741,0.0007139309,0.0003839631,0.0007438419,0.0003588536],"domain_scores_gemma":[0.9934427,0.001075812,0.001821931,0.000191962,0.003415187,0.0000524613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000168217,0.000390546,0.1068111,0.0006959243,0.000408219,2.269329e-7,0.01087059,0.5770511,0.002810027,0.2903166,0.008925325,0.001552085],"study_design_scores_gemma":[0.0009118663,0.0001438653,0.00509948,0.0001779186,0.0001076477,0.000004154382,0.0005694406,0.9685857,0.001653419,0.01196988,0.01048826,0.0002884082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8915835,0.0006541027,0.05876946,0.006893029,0.01290446,0.007030698,0.001372345,0.000681961,0.02011042],"genre_scores_gemma":[0.9335267,4.638926e-7,0.06460079,0.0001335796,0.0003634515,0.00009415534,0.00001232671,0.0000277265,0.001240836],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3915346,"threshold_uncertainty_score":0.9940767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01350295399108917,"score_gpt":0.247305549832438,"score_spread":0.2338025958413488,"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."}}