{"id":"W7117147504","doi":"10.1057/s41599-025-05924-3","title":"Large Language Models in Legal Systems: A Survey","year":2025,"lang":"en","type":"article","venue":"Humanities and Social Sciences Communications","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Brock University; Ontario Tech University","funders":"","keywords":"Perspective (graphical); Key (lock); Reliability (semiconductor); Domain (mathematical analysis); Compliance (psychology)","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.002643581,0.0000704803,0.0001398638,0.000139778,0.004455388,0.0004907256,0.0009501742,0.00007220502,0.00003544431],"category_scores_gemma":[0.0001401819,0.00007373894,0.00002814486,0.0005618351,0.002610229,0.0005073303,0.000286229,0.0001528239,0.0000057095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009926871,"about_ca_system_score_gemma":0.0002657,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1051909,"about_ca_topic_score_gemma":0.532305,"domain_scores_codex":[0.9982915,0.0007931644,0.0002360203,0.0001530384,0.0002148462,0.0003114274],"domain_scores_gemma":[0.9990368,0.0005601962,0.0000604106,0.0002307177,0.00009530801,0.00001649549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.000001202805,0.00003570925,0.001555893,0.000003861486,0.000002773963,2.326284e-7,0.07310683,0.00001610697,0.000001307748,0.9245808,0.0004491828,0.0002460619],"study_design_scores_gemma":[0.00009995682,0.00001791107,0.004662015,0.00005930357,0.00000917212,1.869025e-7,0.7541084,0.007177211,0.000001806731,0.05195584,0.1816796,0.0002286068],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1712403,0.003631104,0.0007387385,0.007040872,0.0003567956,0.0004806783,0.00006564919,0.0001160726,0.8163297],"genre_scores_gemma":[0.9955842,0.0004687726,0.00006751918,0.0004141601,0.00004000844,0.00003880866,0.000009279695,0.000003038174,0.003374134],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.872625,"threshold_uncertainty_score":0.9968407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2769265717469936,"score_gpt":0.4310303258272045,"score_spread":0.1541037540802108,"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."}}