{"id":"W4385571397","doi":"10.18653/v1/2023.clinicalnlp-1.36","title":"WangLab at MEDIQA-Chat 2023: Clinical Note Generation from Doctor-Patient Conversations using Large Language Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; University Health Network; Sunnybrook Health Science Centre; Vector Institute; University of Toronto","funders":"Alliance de recherche numérique du Canada","keywords":"Computer science; Task (project management); Scrutiny; Context (archaeology); Language model; Natural language processing; Path (computing); Artificial intelligence; Human–computer interaction; Multimedia; World Wide Web; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004210229,0.0001291859,0.0001752183,0.00009453588,0.0001945498,0.0001023022,0.0003711361,0.0001155803,0.0002126952],"category_scores_gemma":[0.0000593222,0.000119745,0.00009140937,0.000303356,0.00002102383,0.0005431456,0.0005716096,0.0001273119,0.0003971824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001201103,"about_ca_system_score_gemma":0.00007952945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005602756,"about_ca_topic_score_gemma":0.0005268348,"domain_scores_codex":[0.9982035,0.0001166382,0.0004411575,0.000526168,0.0004054207,0.0003071281],"domain_scores_gemma":[0.9988861,0.0001568585,0.00009416651,0.0006602702,0.00007510959,0.0001275107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003348186,0.0004386471,0.005898658,0.00003180511,0.0002743451,0.0003994214,0.05978593,0.4267486,0.05837345,0.3195271,0.04858075,0.07990775],"study_design_scores_gemma":[0.0003498041,0.00001600012,0.0001349606,0.000007441328,0.000008429176,0.00000138431,0.0001089721,0.9953061,0.001527606,0.001103271,0.001288828,0.0001471932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4338154,0.00003786657,0.5638219,0.0005339136,0.001027098,0.0001043251,0.00001869742,0.0002169009,0.0004239647],"genre_scores_gemma":[0.896853,0.00002083735,0.1002903,0.0009546207,0.0004953126,0.000009478675,0.0001058293,0.00001369431,0.001256869],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5685575,"threshold_uncertainty_score":0.5105109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1173792312521115,"score_gpt":0.3526829460646227,"score_spread":0.2353037148125112,"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."}}