{"id":"W4406113723","doi":"10.2196/68347","title":"The Feasibility of Large Language Models in Verbal Comprehension Assessment: Mixed Methods Feasibility Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Comprehension; Psychology; Proof of concept; Computer science; Natural language processing; Cognitive psychology; Programming language; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.1435678,0.001573792,0.00134673,0.001207602,0.001009096,0.002312032,0.001547044,0.001298932,0.001876496],"category_scores_gemma":[0.1250278,0.001230511,0.00249552,0.0007925315,0.001403289,0.002349269,0.002232748,0.001175387,0.0005019614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001521048,"about_ca_system_score_gemma":0.003407176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001622914,"about_ca_topic_score_gemma":0.003486105,"domain_scores_codex":[0.8716212,0.1129747,0.003701525,0.003645563,0.00700871,0.001048264],"domain_scores_gemma":[0.8456743,0.1192677,0.009991188,0.01405453,0.008995422,0.002016864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.07587899,0.08479059,0.3282631,0.005562756,0.006120503,0.001270941,0.04582617,0.009695115,0.01892783,0.005465917,0.002892221,0.4153059],"study_design_scores_gemma":[0.03549832,0.4283478,0.3974097,0.001609765,0.005678248,0.00138179,0.01525205,0.06381443,0.01916773,0.0100234,0.02081764,0.0009991686],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9322214,0.0004247909,0.04110221,0.0002256009,0.0001043791,0.02372675,0.0002383956,0.00009449403,0.001862083],"genre_scores_gemma":[0.8294216,0.0002177662,0.09620151,0.0003564643,0.0001067984,0.07263386,0.0002562081,0.00006162985,0.0007441256],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1435678,"threshold_uncertainty_score":0.7592679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1752930933309048,"score_gpt":0.5563676749738761,"score_spread":0.3810745816429713,"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."}}