{"id":"W4408185169","doi":"10.1007/s44163-024-00167-8","title":"Legal large language models (LLMs): legal dynamos or “fancifully packaged ChatGPT”?","year":2025,"lang":"en","type":"article","venue":"Discover Artificial Intelligence","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Government of Saskatchewan","funders":"","keywords":"Dynamo; Linguistics; Philosophy; Physics","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":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001972675,0.000537466,0.0006153517,0.0003603103,0.001812008,0.001099968,0.001553289,0.0004067854,0.002514673],"category_scores_gemma":[0.001429502,0.0004966607,0.0003672012,0.001959763,0.001250013,0.002360123,0.0003618011,0.0007438364,0.001083373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004662068,"about_ca_system_score_gemma":0.001509966,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01667071,"about_ca_topic_score_gemma":0.09741183,"domain_scores_codex":[0.994328,0.0005397354,0.001219026,0.00109768,0.001144589,0.001670934],"domain_scores_gemma":[0.99742,0.0006243166,0.0002620344,0.0009566786,0.0003798133,0.0003571822],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003354951,0.0004086317,0.0001125873,0.0000286166,0.00006245142,0.0001406478,0.0152374,0.001467954,0.0009188529,0.9469821,0.001608362,0.03269685],"study_design_scores_gemma":[0.0001874226,0.0003463581,0.00008162926,0.0004949336,0.0002367815,0.00001100293,0.1892093,0.06278373,0.1287193,0.3514189,0.2640006,0.002509959],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1265769,0.000615404,0.5728301,0.005646392,0.005041964,0.001966691,0.0002475095,0.0008554335,0.2862196],"genre_scores_gemma":[0.9734852,0.0001419717,0.0005698783,0.001476035,0.0007624591,0.0001265245,0.00003253729,0.00005671589,0.02334864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8469083,"threshold_uncertainty_score":0.999937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04359948629906125,"score_gpt":0.377597280615294,"score_spread":0.3339977943162328,"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."}}