{"id":"W4406887664","doi":"10.2196/59823","title":"The Clinicians’ Guide to Large Language Models: A General Perspective With a Focus on Hallucinations","year":2025,"lang":"en","type":"article","venue":"Interactive Journal of Medical Research","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":107,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Psychology; Multitude; Scale (ratio); Medicine; Psychiatry; Computer science; Political science; Artificial intelligence","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005835045,0.00009228766,0.0002359236,0.0005432202,0.000310823,0.00006496486,0.0003710466,0.0001121525,0.00017884],"category_scores_gemma":[0.01779989,0.0000506383,0.0001008263,0.0006994612,0.0001633729,0.0001188394,0.00007718915,0.001909463,0.00004707024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008834343,"about_ca_system_score_gemma":0.002923023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001758027,"about_ca_topic_score_gemma":0.001974602,"domain_scores_codex":[0.9963056,0.0004847307,0.0005793383,0.0001863311,0.002044044,0.0003999625],"domain_scores_gemma":[0.9909397,0.00447894,0.0001212339,0.0002563142,0.003774698,0.0004291334],"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":[0.01346382,0.002637529,0.002163451,0.00006103671,0.0007749185,0.001030386,0.04378344,0.0001292415,0.0003321143,0.185534,0.190227,0.5598631],"study_design_scores_gemma":[0.002330213,0.01778855,0.01066748,0.01020375,0.0001977178,0.0005889595,0.6066299,0.02492902,0.01754362,0.09839252,0.2103225,0.0004058201],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.4025644,0.001173879,0.01964138,0.5287658,0.0007600255,0.0007200502,0.000005250664,0.00001234726,0.04635687],"genre_scores_gemma":[0.9920935,0.0004138661,0.0002988712,0.002522391,0.0007793139,0.00003503199,7.369993e-7,0.00001136422,0.003844913],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5895291,"threshold_uncertainty_score":0.9904736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2173770784252622,"score_gpt":0.6187501466348436,"score_spread":0.4013730682095814,"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."}}