{"id":"W4398266979","doi":"10.1080/09695958.2024.2356084","title":"Much ado about hallucinations: a brief assessment of the judicial response to large language model (LLM) hallucinations in the United States and Canada","year":2024,"lang":"en","type":"article","venue":"International Journal of the Legal Profession","topic":"Mental Health and Psychiatry","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Government of Saskatchewan","funders":"","keywords":"Political science; Psychology; Law","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001075375,0.00007932369,0.00009345686,0.0001680515,0.0002680163,0.0001268848,0.0004663221,0.00002478366,0.00007612127],"category_scores_gemma":[0.00009098385,0.00003822011,0.00005673937,0.00009495675,0.00004466307,0.0001624424,0.00009520098,0.0004041943,5.485845e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001870473,"about_ca_system_score_gemma":0.0008250472,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.07438613,"about_ca_topic_score_gemma":0.3599541,"domain_scores_codex":[0.9984037,0.0003577461,0.0003919851,0.00007934673,0.0006481062,0.0001191687],"domain_scores_gemma":[0.9992067,0.0002423067,0.0001814848,0.0001129266,0.0002182061,0.00003832978],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001412896,0.0008707121,0.005558501,0.0002691474,0.0002280437,0.00008441223,0.1799383,0.003943309,0.0007347779,0.6931923,0.1107513,0.003016351],"study_design_scores_gemma":[0.004153734,0.0005936982,0.1688629,0.00813505,0.0001619668,0.0001846857,0.1354661,0.1395589,0.0003180324,0.02226316,0.5197796,0.0005221074],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9100533,0.0002869594,0.0001084721,0.08482888,0.002797371,0.0002359402,0.0001784684,0.000003680785,0.001506984],"genre_scores_gemma":[0.9925682,0.00002321445,0.00004722372,0.00468353,0.0002856029,0.000008534731,0.00000927155,0.000007495035,0.002366932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6709291,"threshold_uncertainty_score":0.9317776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01825250104352276,"score_gpt":0.3511880407876327,"score_spread":0.3329355397441099,"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."}}