{"id":"W4401043383","doi":"10.18653/v1/2024.clinicalnlp-1.49","title":"Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding Large Language Models with Hints","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Canadian Institute of Steel Construction; UK Research and Innovation; Nvidia; Accenture; Cisco Systems","keywords":"Natural language processing; Computer science; Artificial intelligence; Linguistics; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.006139224,0.001751198,0.00109709,0.001520997,0.001021766,0.00410332,0.001987158,0.002936271,0.05003808],"category_scores_gemma":[0.04577396,0.001244657,0.002251257,0.001145414,0.0006923292,0.003734205,0.002922045,0.003637034,0.02482119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0018346,"about_ca_system_score_gemma":0.005267612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01646234,"about_ca_topic_score_gemma":0.02644371,"domain_scores_codex":[0.9951181,0.002907653,0.0002609986,0.0009555688,0.0005613249,0.0001963232],"domain_scores_gemma":[0.9809307,0.0151436,0.0003136718,0.001318164,0.001693246,0.0006006017],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002068547,0.0003448854,0.007907934,0.001749931,0.0003699625,0.0006473522,0.001424618,0.05056933,0.007344491,0.02716462,0.5676796,0.3327286],"study_design_scores_gemma":[0.000661774,0.0002228613,0.001452664,0.000384041,0.0003139722,0.000552169,0.0007196417,0.717797,0.01288452,0.101109,0.1637668,0.0001355692],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0185278,0.001534607,0.7634826,0.01493003,0.001019574,0.0008806825,0.06848463,0.1178526,0.0132875],"genre_scores_gemma":[0.2644695,0.0008358918,0.6232252,0.0033469,0.0005272158,0.0008658661,0.07583637,0.0160838,0.01480928],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05003808,"threshold_uncertainty_score":0.167394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06622473689383701,"score_gpt":0.334065904672627,"score_spread":0.26784116777879,"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."}}