{"id":"W4389519983","doi":"10.18653/v1/2023.findings-emnlp.518","title":"Impact of Co-occurrence on Factual Knowledge of Large Language Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Computer science; Subject (documents); Recall; Object (grammar); Set (abstract data type); Natural language processing; Artificial intelligence; Cognitive psychology; Machine learning; Psychology; World Wide Web; Programming 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002245114,0.00008266032,0.0001532566,0.0001408111,0.00001945666,0.0000111496,0.0005365973,0.00003567458,0.00005118865],"category_scores_gemma":[0.00003036402,0.00006322723,0.00008999782,0.0003187802,0.00001585004,0.0001797408,0.0001640622,0.0000681384,0.00007755743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001944009,"about_ca_system_score_gemma":0.00008373426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000721389,"about_ca_topic_score_gemma":0.000007494732,"domain_scores_codex":[0.9992193,0.00002869222,0.0001880004,0.0002006136,0.0001547878,0.0002086018],"domain_scores_gemma":[0.9992618,0.0001095866,0.00005677943,0.0004720344,0.00004833949,0.00005148266],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004996547,0.001408651,0.009037467,0.0003241469,0.0002124102,0.00003416081,0.1060814,0.114983,0.01863059,0.5354421,0.02624707,0.1875491],"study_design_scores_gemma":[0.0002486967,0.0001303733,0.001915503,0.00002306296,0.000001619879,7.932513e-7,0.0001296342,0.9910436,0.005365066,0.001012863,0.00003374989,0.00009498412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.641748,0.00002145572,0.3500163,0.00001699032,0.00007377391,0.00006216192,0.00006472621,0.0001159376,0.007880579],"genre_scores_gemma":[0.9980687,0.000004226164,0.00158205,0.00001273565,0.0000131803,0.000001899781,0.000007672574,0.00000306347,0.0003064891],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8760607,"threshold_uncertainty_score":0.2578332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05633991273695763,"score_gpt":0.3657026951171723,"score_spread":0.3093627823802148,"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."}}