{"id":"W4404783146","doi":"10.18653/v1/2024.emnlp-main.953","title":"Measuring Psychological Depth in Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Computer science; Natural language processing; Language model; Artificial intelligence; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007398407,0.00002813604,0.00005320772,0.00007613557,0.00004605652,0.00005876249,0.00007452693,0.00002792247,0.0003514687],"category_scores_gemma":[0.00004557714,0.00002243099,0.0000434742,0.0003819412,0.00002789782,0.00009783992,0.00001239968,0.00006215667,0.00005986808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002769292,"about_ca_system_score_gemma":0.00001921525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001177368,"about_ca_topic_score_gemma":0.004582105,"domain_scores_codex":[0.9994075,0.0001291684,0.00007451343,0.0001224484,0.000166991,0.00009942515],"domain_scores_gemma":[0.9997678,0.0001507571,0.000004437596,0.00003446592,0.00001083131,0.00003173525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001893505,0.00003016021,0.0005606977,0.000003212084,0.000008662807,0.00003673807,0.009524764,0.001803158,0.00006552161,0.5294691,0.0001939293,0.4583021],"study_design_scores_gemma":[0.0001847528,0.00002110028,0.02153342,0.00005179183,0.00001965289,0.000002831491,0.008508638,0.2159809,0.00006347388,0.740361,0.01296724,0.000305221],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.249986,0.0007325615,0.07814199,0.001375104,0.00014396,0.00004605547,2.660786e-7,0.0001512056,0.6694229],"genre_scores_gemma":[0.9897385,0.00001698854,0.006656357,0.00009011553,0.00009381755,0.00000298814,5.80292e-7,0.000001954074,0.003398743],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7397525,"threshold_uncertainty_score":0.3848335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2191795032686007,"score_gpt":0.4647030931911161,"score_spread":0.2455235899225154,"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."}}