{"id":"W4416466606","doi":"10.1038/s43588-025-00913-7","title":"Viability of using LLMs as models of human language processing","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Human language; Language model; Language technology; Universal Networking Language; On Language; Computational linguistics; Work (physics)","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":[0.001025555,0.0004741134,0.0006261008,0.0003713228,0.0003435557,0.00132273,0.001263798,0.001056591,0.003519938],"category_scores_gemma":[0.005339061,0.0002502268,0.000534528,0.0002131335,0.0008637176,0.002510374,0.0008067787,0.001107236,0.0007019282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007289943,"about_ca_system_score_gemma":0.0007953081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001691296,"about_ca_topic_score_gemma":0.001605748,"domain_scores_codex":[0.9996501,0.0002189763,0.00001076518,0.00004034424,0.00005469523,0.00002512601],"domain_scores_gemma":[0.9976823,0.001613444,0.00008521145,0.0003327342,0.0001627487,0.000123666],"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":[0.0002097717,0.00009512157,0.001496023,0.0001255494,0.0001023102,0.000106135,0.0002168447,0.4339481,0.005786403,0.5320603,0.00169304,0.02416043],"study_design_scores_gemma":[0.00001122357,0.00002039375,0.00008780479,0.000004527791,0.000006228593,0.00001425913,0.00001452788,0.837988,0.000545482,0.1605478,0.0007547431,0.000005057131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1315018,0.0004970921,0.8346887,0.002982917,0.0002124936,0.00005237938,0.0002321312,0.001023461,0.0288091],"genre_scores_gemma":[0.9334785,0.0002334832,0.05930166,0.0002534257,0.0001162003,0.0001010544,0.00008761969,0.0001632136,0.006264956],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003519938,"threshold_uncertainty_score":0.01177543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02732870010255197,"score_gpt":0.3824924493057228,"score_spread":0.3551637492031708,"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."}}