{"id":"W6929165052","doi":"10.48448/xw64-j335","title":"The Troubling Emergence of Hallucination in Large Language Models - An Extensive Definition, Quantification, and Prescriptive Remediations","year":2023,"lang":"en","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Categorization; Acronym; Vulnerability (computing); Rank (graph theory); Profiling (computer programming)","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":[0.0120898,0.001283927,0.00105178,0.002182503,0.001423775,0.005578431,0.002049128,0.001704244,0.001930351],"category_scores_gemma":[0.06669252,0.0009623473,0.001320868,0.001810022,0.003569174,0.007530484,0.007088842,0.004397766,0.001521031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001269379,"about_ca_system_score_gemma":0.00187971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003763284,"about_ca_topic_score_gemma":0.007476677,"domain_scores_codex":[0.9836166,0.01015635,0.001501879,0.001878972,0.002484626,0.0003615099],"domain_scores_gemma":[0.93685,0.04676327,0.002509217,0.01033205,0.002885136,0.0006602502],"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":[0.001152693,0.0002704575,0.05598557,0.005018386,0.0007569523,0.004533033,0.02325771,0.06126076,0.02870085,0.1547719,0.06846061,0.5958311],"study_design_scores_gemma":[0.0001334057,0.00028083,0.01182168,0.001842435,0.0002444135,0.004684645,0.008333499,0.4580182,0.02184999,0.308094,0.1842827,0.0004140934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1137276,0.01154966,0.8262331,0.0161592,0.0006542707,0.0003987518,0.01055951,0.01121629,0.009501688],"genre_scores_gemma":[0.6895528,0.004076579,0.2820271,0.003477732,0.0004621698,0.0005170688,0.01485216,0.001860453,0.003174038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0120898,"threshold_uncertainty_score":0.06393778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.11602306746098,"score_gpt":0.3573935314328296,"score_spread":0.2413704639718496,"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."}}