{"id":"W4319301677","doi":"10.1162/neco_a_01563","title":"Large Language Models and the Reverse Turing Test","year":2023,"lang":"en","type":"article","venue":"Neural Computation","topic":"Topic Modeling","field":"Computer Science","cited_by":164,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Psychology; Cognitive psychology; Computer science; Cognitive science","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":[],"consensus_categories":[],"category_scores_codex":[0.0002452734,0.00005349039,0.0000618045,0.0000442593,0.0001166273,0.00009821771,0.0001739298,0.00001722712,6.533651e-7],"category_scores_gemma":[0.00004110901,0.00003862588,0.00001989286,0.0002023008,0.00001515459,0.0003022008,0.000178131,0.00007729839,0.00001699867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007766363,"about_ca_system_score_gemma":0.000005982151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002330912,"about_ca_topic_score_gemma":0.000005385451,"domain_scores_codex":[0.999433,0.00004550986,0.00009505702,0.0001681331,0.0001289055,0.0001293629],"domain_scores_gemma":[0.9995604,0.0002208128,0.00003208293,0.0001439395,0.0000198093,0.00002302692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001396753,0.00002600151,0.0004812433,0.0000547882,0.0000116471,0.00007457923,0.03096054,0.7535505,0.0009476605,0.1095319,0.00145526,0.1028919],"study_design_scores_gemma":[0.0004129182,0.000006812925,0.0006743441,0.000005226311,0.000001698364,0.000007441055,0.0001204355,0.9895766,0.00005056538,0.0090726,0.00002657035,0.00004482372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.413798,0.00005034401,0.5833945,0.00197624,0.0001471808,0.0001043383,8.631965e-7,0.0002555418,0.0002730077],"genre_scores_gemma":[0.9958519,0.000005115537,0.003546603,0.0004369744,0.00004936912,0.000004722466,0.000002669873,0.000004013912,0.00009857705],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.582054,"threshold_uncertainty_score":0.1575118,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03063292580025428,"score_gpt":0.2742570784898651,"score_spread":0.2436241526896109,"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."}}