{"id":"W4385574232","doi":"10.18653/v1/2022.nllp-1.10","title":"Parameter-Efficient Legal Domain Adaptation","year":2022,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Domain adaptation; Adaptation (eye); Domain (mathematical analysis); Language model; Artificial intelligence; Legal case; Machine learning; Legal advice; Data science; Law; Mathematics","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008941785,0.0000495958,0.00006008446,0.00004550899,0.001327706,0.00006696251,0.000232443,0.00002140758,0.005509668],"category_scores_gemma":[0.0001378045,0.00005210463,0.00004719508,0.0003260401,0.0001920096,0.00008603877,0.00007294636,0.0001106649,0.0001858594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000195732,"about_ca_system_score_gemma":0.0001387146,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008375955,"about_ca_topic_score_gemma":0.002994585,"domain_scores_codex":[0.9986262,0.0002833173,0.0001512633,0.0001617073,0.0005355144,0.0002420231],"domain_scores_gemma":[0.999558,0.0001810911,0.00004481429,0.0001129521,0.00003718988,0.00006600005],"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":[0.000009554138,0.00007354552,0.0001433216,3.918477e-7,0.000003055601,0.000005835225,0.01942911,0.01805529,0.0001002068,0.9547524,0.0008911466,0.006536158],"study_design_scores_gemma":[0.00003917224,0.00007853485,0.0000879404,0.000001039604,0.000004218964,0.000001412711,0.1605264,0.01469969,0.0003767968,0.02978171,0.794236,0.0001670988],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5969312,0.00002555966,0.04576754,0.004190119,0.001155992,0.0003354835,0.000004996556,0.0002044353,0.3513847],"genre_scores_gemma":[0.991663,0.000001335345,0.00247216,0.0004103599,0.0001014978,0.00005115801,0.000002151095,0.000005759475,0.005292544],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9249707,"threshold_uncertainty_score":0.9999724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06623400985671193,"score_gpt":0.3431375893438574,"score_spread":0.2769035794871455,"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."}}