{"id":"W4405043127","doi":"10.3233/faia241243","title":"Robots in the Middle: Evaluating LLMs in Dispute Resolution","year":2024,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Law, AI, and Intellectual Property","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Université de Montréal; Research Unit on Children's Psychosocial Maladjustment","funders":"","keywords":"Robot; Resolution (logic); Dispute resolution; Political science; Computer security; Computer science; Artificial intelligence; Law","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":[0.0009098219,0.0002513355,0.00028726,0.0004079159,0.0001405934,0.0002619185,0.000961254,0.0002265753,0.00002022147],"category_scores_gemma":[0.00004913241,0.0001972688,0.00007353773,0.0004876637,0.00028418,0.0002267693,0.0002073905,0.0006737802,0.0001303985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001509332,"about_ca_system_score_gemma":0.00009682744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001255117,"about_ca_topic_score_gemma":0.0005836083,"domain_scores_codex":[0.9978812,0.00005933968,0.0007020436,0.0007306499,0.0003080616,0.0003187328],"domain_scores_gemma":[0.9990617,0.0001448596,0.0001055122,0.0005871311,0.00005309098,0.00004770805],"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":[0.000007775603,0.00004536676,0.00001110319,0.0000333169,0.000007088072,0.000006531282,0.003055571,0.001044346,0.00001618441,0.7181877,0.001347785,0.2762372],"study_design_scores_gemma":[0.00001654936,0.00005233931,0.000009456193,0.0002450814,0.000009894396,0.000004388143,0.0004353034,0.2859876,0.00006202725,0.6845166,0.02842172,0.0002389979],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00004584933,0.004998695,0.8881519,0.001544459,0.0005663812,0.001252476,0.00001049325,0.00005805898,0.1033717],"genre_scores_gemma":[0.4970669,0.0256771,0.1610247,0.005343013,0.004124966,0.006671359,0.0003477643,0.0004350663,0.299309],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7271272,"threshold_uncertainty_score":0.804439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1283407056102637,"score_gpt":0.3060759424114476,"score_spread":0.177735236801184,"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."}}