{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006807937,0.00008121033,0.00008453675,0.00009281669,0.0001503458,0.0001664938,0.0004686571,0.00005853724,0.0001695607],"category_scores_gemma":[0.00005443739,0.00007652491,0.00004061701,0.0003549663,0.00001280279,0.0001900915,0.0001694845,0.0001075479,0.0000746298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007242672,"about_ca_system_score_gemma":0.00008896054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002296164,"about_ca_topic_score_gemma":0.00006470061,"domain_scores_codex":[0.9987292,0.0000576833,0.0001349167,0.0003092702,0.000525914,0.0002429706],"domain_scores_gemma":[0.9993236,0.00004885145,0.00003325839,0.0004468995,0.00008830163,0.00005910555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[2.907318e-7,0.0000107047,0.001180438,0.000009000846,0.00001173385,0.000005789587,0.003729548,0.002806003,0.0006027207,0.9752036,0.001472747,0.01496737],"study_design_scores_gemma":[0.0001015206,0.00001383727,0.003943687,0.0000126684,0.000003655011,0.000002195977,0.00009948695,0.8998116,0.0003046704,0.0951751,0.00040836,0.0001232436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4891649,0.00001485432,0.4993829,0.004963478,0.0004669479,0.0001377509,9.534678e-7,0.0004685916,0.005399628],"genre_scores_gemma":[0.9569598,0.000001585166,0.03820462,0.0008888418,0.0002726472,0.00003954504,0.000007326436,0.000006904335,0.003618708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8970056,"threshold_uncertainty_score":0.3120595,"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."}}