{"id":"W4376632853","doi":"10.48550/arxiv.2305.07507","title":"LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Innovationsfonden","keywords":"Multinational corporation; Upstream (networking); Benchmark (surveying); Downstream (manufacturing); Computer science; Work (physics); Natural language processing; Knowledge management; Artificial intelligence; Business; Engineering; Marketing; Geography; Finance","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007567321,0.0002226663,0.0002242659,0.0001827539,0.0007475597,0.0001749763,0.0005181,0.0002906557,0.00008133569],"category_scores_gemma":[0.0008139589,0.0002845939,0.00009059257,0.0002775227,0.0005110674,0.0003658426,0.0007261484,0.0004577968,0.00009220828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003636392,"about_ca_system_score_gemma":0.0006767606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003839051,"about_ca_topic_score_gemma":0.01025789,"domain_scores_codex":[0.9982536,0.0001666726,0.0002425933,0.0007283295,0.0002114034,0.0003974429],"domain_scores_gemma":[0.9987126,0.0003898355,0.0001614134,0.0002371383,0.000332913,0.0001661247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002259786,0.0000586435,0.002431119,0.00007018689,0.00007508075,0.00012157,0.1054086,0.4072044,0.00003668957,0.4821185,0.0004108247,0.002041892],"study_design_scores_gemma":[0.0002933,0.00002292108,0.0009839792,0.0002572273,0.00008503936,5.333083e-7,0.1552182,0.7857664,0.0004450655,0.04275752,0.01279412,0.001375725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9523497,0.00004193961,0.03013891,0.0001265183,0.0005598816,0.0003622886,0.0000610659,0.0004317291,0.01592802],"genre_scores_gemma":[0.978471,0.00005751584,0.00259873,0.0000301679,0.0001866032,0.000003080956,0.00003850115,0.00002173541,0.01859271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4393609,"threshold_uncertainty_score":0.9999606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1709450320481825,"score_gpt":0.2690160056562647,"score_spread":0.09807097360808217,"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."}}