{"id":"W4389519325","doi":"10.18653/v1/2023.findings-emnlp.84","title":"Can ChatGPT Assess Human Personalities? A General Evaluation Framework","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Research Foundation Singapore","keywords":"Personality psychology; Correctness; Computer science; Consistency (knowledge bases); Robustness (evolution); Psychology; Social psychology; Personality; Artificial intelligence; Algorithm","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":[0.04707131,0.002006169,0.001139735,0.003180997,0.0008455822,0.003429242,0.00175635,0.002153108,0.003380904],"category_scores_gemma":[0.1834012,0.0004276488,0.001172194,0.001972987,0.001930947,0.005737127,0.003553319,0.002129725,0.0009953713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001502298,"about_ca_system_score_gemma":0.001843303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002156244,"about_ca_topic_score_gemma":0.001661957,"domain_scores_codex":[0.9333373,0.05297546,0.002847634,0.004081422,0.005943344,0.0008148238],"domain_scores_gemma":[0.8392562,0.1263999,0.00689361,0.01448194,0.01050774,0.002460572],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006863373,0.00187568,0.1351597,0.003118885,0.00192933,0.0003781885,0.006944839,0.09900729,0.02418819,0.03727403,0.01575683,0.6675037],"study_design_scores_gemma":[0.0006573058,0.005749628,0.05744288,0.0005728521,0.0008932889,0.0005594412,0.002875718,0.8040806,0.03187544,0.08021031,0.01467512,0.0004074013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2429914,0.001225416,0.7278375,0.001719704,0.0002478147,0.003252232,0.002945768,0.006482511,0.01329777],"genre_scores_gemma":[0.8345131,0.0001634234,0.1587919,0.0003729547,0.0001211937,0.002747618,0.001790821,0.0002847022,0.001214235],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04707131,"threshold_uncertainty_score":0.2489399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1442513789451381,"score_gpt":0.3721872873750639,"score_spread":0.2279359084299258,"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."}}