{"id":"W4415297078","doi":"10.1016/j.mlwa.2025.100758","title":"Prompt design for medical question answering with Large Language Models","year":2025,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Variety (cybernetics); Workflow; Language model; Tree (set theory); Simple (philosophy); Sonnet","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005205864,0.0001160542,0.00012374,0.00009616406,0.0002888709,0.00008356124,0.0004596127,0.00005393462,0.00000501001],"category_scores_gemma":[0.00004388505,0.00008967154,0.0000198962,0.0003540051,0.00002189702,0.000177119,0.00008763379,0.0002496222,0.000003855495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000344118,"about_ca_system_score_gemma":0.0001477998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006730083,"about_ca_topic_score_gemma":0.00006403336,"domain_scores_codex":[0.9989537,0.0000582116,0.0001506774,0.0003831189,0.0002226639,0.0002316034],"domain_scores_gemma":[0.9992493,0.0001433965,0.00006319206,0.0003973893,0.0000750562,0.00007165359],"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":[0.00003613309,0.000117831,0.00203783,0.00009217145,0.00004412598,0.000004063654,0.001129422,0.3545157,0.0001644655,0.5687517,0.00006282331,0.07304379],"study_design_scores_gemma":[0.0005030535,0.00006421641,0.00009757365,0.00006937639,0.00001197914,0.000008474551,0.00003294454,0.992052,0.0001305281,0.002717403,0.004199335,0.0001131023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001051992,0.0001622298,0.9947484,0.001938296,0.00001421739,0.0008032837,0.00000176618,0.0004116939,0.0008681081],"genre_scores_gemma":[0.5304747,0.000003637049,0.4675029,0.0001943466,0.00003142633,0.001030496,0.00001565614,0.00001187651,0.0007350235],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6375363,"threshold_uncertainty_score":0.3656699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01004011921151553,"score_gpt":0.2772171588428123,"score_spread":0.2671770396312968,"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."}}