{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005491769,0.0003201764,0.0004256575,0.003146205,0.009127189,0.004116619,0.001579003,0.001798504,0.001334789],"category_scores_gemma":[0.03174591,0.0003214381,0.0003645924,0.003859539,0.003881748,0.001243124,0.002534964,0.00247069,0.0001974234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.03162775,"about_ca_system_score_gemma":0.04445412,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.8850853,"about_ca_topic_score_gemma":0.9598065,"domain_scores_codex":[0.9925656,0.001766029,0.0005837872,0.0003190222,0.003585607,0.001179871],"domain_scores_gemma":[0.9755363,0.00436661,0.001919018,0.0003808445,0.01541734,0.002379876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0006212356,0.0004320108,0.2798169,0.001290303,0.000113282,0.008632973,0.4129164,0.00050608,0.002601627,0.005156852,0.03688719,0.2510251],"study_design_scores_gemma":[0.0000269213,0.0002919678,0.363767,0.0009494472,0.00005227303,0.002064238,0.5772198,0.0003102359,0.0006375627,0.0006495253,0.05390373,0.000127263],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8792762,0.01238362,0.0007160243,0.05624983,0.0006738089,0.0006077359,0.000869764,0.00004874438,0.04917427],"genre_scores_gemma":[0.9722947,0.0114434,0.0003896141,0.01112365,0.000257083,0.00005246116,0.0003458304,0.00002455098,0.004068649],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1149147,"threshold_uncertainty_score":0.2311829,"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."}}