{"id":"W4388787390","doi":"10.48550/arxiv.2311.09308","title":"Divergences between Language Models and Human Brains","year":2023,"lang":"en","type":"preprint","venue":"PubMed","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Deafness and Other Communication Disorders; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; James S. McDonnell Foundation","keywords":"Magnetoencephalography; Computer science; Human language; Narrative; Human brain; Process (computing); Psychology; Cognitive psychology; Natural language processing; Cognitive science; Artificial intelligence; Linguistics; Electroencephalography; Neuroscience","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002449013,0.0002909084,0.0002802703,0.0009441462,0.0003457336,0.001914214,0.0005205046,0.0007153006,0.006049586],"category_scores_gemma":[0.0218463,0.0002034192,0.0003680926,0.000598624,0.001059143,0.002669331,0.0009286621,0.001085536,0.0009187086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007206279,"about_ca_system_score_gemma":0.000489146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001474064,"about_ca_topic_score_gemma":0.001726876,"domain_scores_codex":[0.9986026,0.0008173352,0.00005744064,0.0002343331,0.0002234939,0.0000648553],"domain_scores_gemma":[0.9948618,0.003704499,0.0002684247,0.0005654688,0.000423087,0.0001767757],"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":[0.0007005658,0.0001860543,0.06056771,0.0009758847,0.0009434861,0.001018715,0.01603233,0.08087417,0.04387766,0.5202504,0.01330153,0.2612715],"study_design_scores_gemma":[0.00006783355,0.0001544709,0.04417418,0.0001168264,0.0001114148,0.001040069,0.002893242,0.2215621,0.005787036,0.7120452,0.01194658,0.0001010784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6887928,0.001769559,0.2387285,0.004360066,0.0002301702,0.00005243603,0.00117681,0.0009837144,0.06390598],"genre_scores_gemma":[0.9877396,0.000186476,0.01030617,0.0002256878,0.00001583106,0.00003697268,0.0003881222,0.0000981716,0.00100303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006049586,"threshold_uncertainty_score":0.02023786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1195529722328077,"score_gpt":0.3338850755295991,"score_spread":0.2143321032967915,"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."}}