{"id":"W4389523920","doi":"10.18653/v1/2023.nllp-1.25","title":"A Comparative Study of Prompting Strategies for Legal Text Classification","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Thomson Reuters (Canada)","funders":"","keywords":"Computer science; Domain (mathematical analysis); Natural language processing; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.000205661,0.00004940792,0.000105836,0.00006584589,0.00005754689,0.00008729633,0.0002896417,0.0000139017,0.000001787377],"category_scores_gemma":[0.000007453389,0.00004158017,0.0000179287,0.0002562267,0.000009148647,0.0003657799,0.0000729593,0.00003173346,0.000009158418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009310813,"about_ca_system_score_gemma":0.00005679302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005770396,"about_ca_topic_score_gemma":0.00006891967,"domain_scores_codex":[0.9993707,0.00002467158,0.0001765591,0.0001975999,0.0001243611,0.0001061117],"domain_scores_gemma":[0.999527,0.00008291374,0.00006396657,0.0002286154,0.00008211443,0.00001543362],"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":[0.000009005204,0.0002714388,0.0009057294,0.00004324674,0.00003714592,0.000001256778,0.0311616,0.01156326,0.008064056,0.9351333,0.0006945286,0.01211545],"study_design_scores_gemma":[0.0002522305,0.0001518986,0.005714303,0.00000495549,0.000002247474,3.441034e-7,0.02228211,0.968102,0.0004215733,0.002926104,0.00008772577,0.0000544615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4875987,0.000001557664,0.5094973,0.00014253,0.00004901936,0.0003238614,2.565819e-7,0.0001177966,0.002268952],"genre_scores_gemma":[0.9751264,1.276364e-7,0.02445125,0.000007974893,0.00001924952,0.00006791211,7.952513e-7,0.000002114342,0.0003241223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9565388,"threshold_uncertainty_score":0.169559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2001642454534,"score_gpt":0.3770997134860705,"score_spread":0.1769354680326705,"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."}}