{"id":"W7117645573","doi":"10.1109/wincom65874.2025.11313356","title":"Ranking Large Language Models with Human Preferences: A Game-Theoretic and Bayesian Comparative Study","year":2025,"lang":"","type":"article","venue":"","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Ranking (information retrieval); Pairwise comparison; Transitive relation; Convergence (economics); Bayesian probability; Ranking SVM; Scalability; Preference; Sensitivity (control systems)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04531256,0.001354237,0.001799686,0.003558229,0.001554908,0.003803704,0.002319236,0.002276156,0.00376667],"category_scores_gemma":[0.1422733,0.0008338892,0.001270718,0.002134731,0.003382827,0.009063877,0.002942411,0.003333015,0.00038438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006228962,"about_ca_system_score_gemma":0.002991915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02039529,"about_ca_topic_score_gemma":0.02246897,"domain_scores_codex":[0.9734884,0.02214957,0.0004964214,0.001314497,0.002014413,0.0005366909],"domain_scores_gemma":[0.7485263,0.2378821,0.002808349,0.004240417,0.00501698,0.001525885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001056529,0.0007421656,0.01442144,0.0007777094,0.0006379854,0.0002156614,0.001582556,0.6810083,0.0009646456,0.2033154,0.005586158,0.08969148],"study_design_scores_gemma":[0.00005090328,0.0001823551,0.001538189,0.00004866294,0.0000449309,0.00005592002,0.0002803402,0.9498647,0.0002689747,0.04648345,0.001141703,0.0000397882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4417922,0.006187234,0.5251516,0.005429829,0.0001445845,0.0007088207,0.0005429244,0.0003697703,0.01967304],"genre_scores_gemma":[0.8874651,0.0008213327,0.1080193,0.0005122031,0.0001312035,0.0003335325,0.0004995403,0.0001309468,0.00208686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04531256,"threshold_uncertainty_score":0.2396386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02112583726665783,"score_gpt":0.2886566296831123,"score_spread":0.2675307924164545,"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."}}