{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00175566,0.0002251848,0.0001890232,0.0003949972,0.0003514835,0.001097113,0.0001347205,0.0003148576,0.002110676],"category_scores_gemma":[0.0139925,0.0001319139,0.0002394792,0.0002131294,0.0002454757,0.0006397893,0.0004822307,0.0003580693,0.0005796775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001201116,"about_ca_system_score_gemma":0.0001573441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008674675,"about_ca_topic_score_gemma":0.001264072,"domain_scores_codex":[0.999086,0.0004507334,0.00007588375,0.0001118647,0.0001672698,0.0001083534],"domain_scores_gemma":[0.9905069,0.004918799,0.001833242,0.0007522457,0.000727153,0.001261594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000624409,0.0001716887,0.9581193,0.00004548438,0.0000627125,0.0001553772,0.007162518,0.0003140105,0.007511288,0.0001015448,0.0002932443,0.02543854],"study_design_scores_gemma":[0.0000134148,0.0004541645,0.9899709,0.000016072,0.00002796266,0.0002430375,0.005330282,0.00215076,0.0009428608,0.000249759,0.0005795265,0.00002124683],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9987521,0.00002183886,0.0005503807,0.00003456255,0.000003100657,0.000008630672,0.00002140784,0.000006730555,0.0006010776],"genre_scores_gemma":[0.9993123,0.00001445564,0.0003334591,0.00001821873,0.000002620105,0.000008484761,0.0000278904,0.000003964942,0.0002786426],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002110676,"threshold_uncertainty_score":0.009284914,"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."}}