{"id":"W4402473640","doi":"10.1109/ccece59415.2024.10667245","title":"Adapting Large Language Models for Automatic Annotation of Radiology Reports for Metastases Detection","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Annotation; Artificial intelligence; Natural language processing","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":[0.0006383665,0.0000597054,0.0001196881,0.00009735487,0.00004196107,0.00003769371,0.00009178113,0.00003331391,0.000003654969],"category_scores_gemma":[0.000105281,0.0000513493,0.00007112073,0.0001061495,0.000005138097,0.0003488068,0.00003124489,0.00002708143,5.204679e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002021218,"about_ca_system_score_gemma":0.00003473281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002111322,"about_ca_topic_score_gemma":0.00001953063,"domain_scores_codex":[0.9992442,0.00002336295,0.0002792854,0.0002404148,0.0000718573,0.0001408795],"domain_scores_gemma":[0.9994071,0.0002389046,0.00007369147,0.0002079785,0.00005434873,0.000018007],"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":[0.000008828199,0.00004665042,0.000009599406,0.0008051937,0.0001128988,0.00002572506,0.006583302,0.0485755,0.03270499,0.2532369,0.0004728674,0.6574175],"study_design_scores_gemma":[0.00008821204,0.00005411584,0.000003281385,0.00002112324,0.00001402066,0.00005535879,0.0001329447,0.964939,0.01648533,0.01805808,0.00009496712,0.00005357858],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02553105,0.0003767207,0.972966,0.00007969216,0.000365069,0.0003465569,0.000006511488,0.0002136334,0.0001147894],"genre_scores_gemma":[0.6888052,7.02067e-7,0.3109728,0.00002513947,0.0000354542,0.00006386323,0.000004080349,0.000004743068,0.00008792672],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9163635,"threshold_uncertainty_score":0.2093964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03076148918633741,"score_gpt":0.2961688213673668,"score_spread":0.2654073321810294,"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."}}