{"id":"W4416037110","doi":"10.18653/v1/2025.emnlp-main.71","title":"Personality Matters: User Traits Predict LLM Preferences in Multi-Turn Collaborative Tasks","year":2025,"lang":"","type":"article","venue":"","topic":"Team Dynamics and Performance","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Personality; Big Five personality traits; Affect (linguistics); Matching (statistics); Task (project management)","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000734154,0.0005633605,0.0007210553,0.0003958197,0.000198975,0.0001921949,0.0006753898,0.0006116586,0.007130702],"category_scores_gemma":[0.00005908527,0.0005140766,0.0001455765,0.001501272,0.0003943994,0.000297391,0.0001571376,0.0009077453,0.0002609575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001921331,"about_ca_system_score_gemma":0.0005376581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001883088,"about_ca_topic_score_gemma":0.01252217,"domain_scores_codex":[0.9961511,0.0006109707,0.0009826665,0.001087647,0.0002999562,0.0008676407],"domain_scores_gemma":[0.9984787,0.0002897597,0.0003429534,0.0005162405,0.0002123122,0.0001600847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001498482,0.004756083,0.8259326,0.0007514323,0.001026965,0.00004761185,0.05619917,0.0002286729,0.0002491312,0.01933449,0.06080516,0.02917017],"study_design_scores_gemma":[0.004158384,0.0003895375,0.9193673,0.0004002623,0.00008149105,0.000003617693,0.01063279,0.0145873,0.00004379152,0.0003696109,0.04938936,0.000576572],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9143938,0.00222294,0.00183392,0.008335552,0.002513604,0.001569677,0.001345193,0.00009393758,0.06769135],"genre_scores_gemma":[0.9567879,0.0004260382,0.001006929,0.00385011,0.00009009371,0.0001728565,0.00004944663,0.00002652765,0.03759006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09343465,"threshold_uncertainty_score":0.9997311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03038290067593673,"score_gpt":0.3395296337577393,"score_spread":0.3091467330818025,"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."}}