{"id":"W4402171959","doi":"10.2196/51319","title":"Assessing the Current Limitations of Large Language Models in Advancing Health Care Education","year":2024,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Health care; Engineering ethics; Computer science; Political science; Engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001507531,0.00005833181,0.0001170487,0.0004146126,0.0001923595,0.0000579995,0.00007331633,0.00003041609,0.00001230152],"category_scores_gemma":[0.0002505977,0.00004096682,0.0000385449,0.0008877268,0.0000591302,0.0005663129,0.0000316873,0.0006450019,0.00002819729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005861375,"about_ca_system_score_gemma":0.002953698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004653333,"about_ca_topic_score_gemma":0.0004204239,"domain_scores_codex":[0.9985427,0.000260522,0.0003614764,0.0001260024,0.000383783,0.0003255296],"domain_scores_gemma":[0.9986141,0.0006489628,0.00004520475,0.0001743867,0.0004377899,0.00007958215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.000006361048,0.0001426891,0.000243993,0.0009250632,0.000003249302,4.561486e-7,0.2825601,0.00003435696,0.00004977968,0.00371906,0.001739539,0.7105753],"study_design_scores_gemma":[0.00005396666,0.0003216304,0.007060325,0.003482648,0.000005675336,0.000006009548,0.9338239,0.03339483,0.001751147,0.0057613,0.01424722,0.00009137399],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9530158,0.02680323,0.002327336,0.01152387,0.000580519,0.001225608,0.00001230079,0.0000332432,0.004478069],"genre_scores_gemma":[0.9983749,0.0008441376,0.0001809618,0.000101213,0.000149598,0.000223043,0.00007170192,0.000009807351,0.00004468605],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.710484,"threshold_uncertainty_score":0.5239733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3951358902688075,"score_gpt":0.6376676475787504,"score_spread":0.2425317573099429,"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."}}