{"id":"W7126026291","doi":"10.1109/bibm66473.2025.11356537","title":"MoCA-Dialog: A Benchmark for Fine-Grained Evaluation of Large Language Models in Clinical Cognitive Assessment Dialogues","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmark (surveying); Cognition; Interpretation (philosophy); Focus (optics); Function (biology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.02197838,0.004016684,0.001394822,0.004163112,0.001396604,0.005357764,0.004719301,0.004034969,0.00879152],"category_scores_gemma":[0.108672,0.0009760267,0.001839126,0.001544812,0.001453572,0.003877295,0.007811785,0.002916664,0.005023302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003176914,"about_ca_system_score_gemma":0.005742017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01613772,"about_ca_topic_score_gemma":0.01559596,"domain_scores_codex":[0.9756236,0.01471069,0.002822348,0.002910713,0.00324128,0.0006914103],"domain_scores_gemma":[0.9452656,0.03809686,0.00172631,0.00552048,0.007047377,0.002343362],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.008693612,0.004038334,0.02832291,0.00828667,0.002188669,0.001211477,0.006237527,0.2530719,0.01839471,0.0136542,0.1434115,0.5124885],"study_design_scores_gemma":[0.00239122,0.003539063,0.01646095,0.001855007,0.0005064101,0.001126855,0.002158555,0.7946044,0.03384919,0.03465938,0.1081069,0.0007420001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3066889,0.01225034,0.4198893,0.003912328,0.002105205,0.006856488,0.05581324,0.1579439,0.03454028],"genre_scores_gemma":[0.5361857,0.001510858,0.3705722,0.001374311,0.0002261988,0.005521114,0.07404551,0.006184386,0.004379698],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02197838,"threshold_uncertainty_score":0.1162342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3373804980580234,"score_gpt":0.5779121950365034,"score_spread":0.24053169697848,"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."}}