{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0169143,0.001404103,0.001178697,0.001230753,0.001092274,0.002951922,0.001726368,0.001385706,0.001791578],"category_scores_gemma":[0.1501991,0.0008971599,0.0009565421,0.00116878,0.001608513,0.005973483,0.003119705,0.003601368,0.001058666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001256495,"about_ca_system_score_gemma":0.001480624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005842099,"about_ca_topic_score_gemma":0.008581834,"domain_scores_codex":[0.9842562,0.007084792,0.001477964,0.004334016,0.002260395,0.0005866672],"domain_scores_gemma":[0.8345807,0.1264883,0.006577327,0.02737236,0.003764448,0.001216805],"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":[0.002386763,0.0005681161,0.2592116,0.001935595,0.001454416,0.001946767,0.004387186,0.1887935,0.02624568,0.008209191,0.02098142,0.4838797],"study_design_scores_gemma":[0.0001940818,0.0008013875,0.06750428,0.0007299344,0.0007699878,0.002509305,0.002428983,0.795422,0.05421058,0.05001327,0.02516281,0.0002534416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7993172,0.005897488,0.1686962,0.002932135,0.0006172689,0.00027633,0.003426593,0.01298146,0.005855309],"genre_scores_gemma":[0.95854,0.0004102898,0.03483276,0.000600266,0.0001004371,0.0001467041,0.003537467,0.0008323805,0.0009997505],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0169143,"threshold_uncertainty_score":0.08945251,"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."}}