{"id":"W4392669746","doi":"10.18653/v1/2023.ijcnlp-srw.12","title":"Evaluating Large Language Models’ Understanding of Financial Terminology via Definition Modeling","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institute of Advanced Industrial Science and Technology; Nvidia","keywords":"Terminology; Computer science; Computational linguistics; Linguistics; Natural language processing; Philosophy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01225194,0.001665079,0.001253506,0.003956976,0.001256028,0.006327162,0.002577445,0.001983283,0.003381738],"category_scores_gemma":[0.04811329,0.001037405,0.00272081,0.002937444,0.000894553,0.01280154,0.003531301,0.003439442,0.001395956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002335088,"about_ca_system_score_gemma":0.001827781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008999459,"about_ca_topic_score_gemma":0.01306918,"domain_scores_codex":[0.9879761,0.008611389,0.0006959424,0.001477178,0.001005633,0.0002337055],"domain_scores_gemma":[0.9458712,0.04773547,0.001054021,0.002411077,0.002257304,0.000670961],"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":[0.002946612,0.001278211,0.03282157,0.001514671,0.002118145,0.0009319363,0.006146106,0.3480887,0.008827494,0.08023664,0.05859645,0.4564935],"study_design_scores_gemma":[0.0001327525,0.0001191107,0.0023371,0.00006602793,0.000221324,0.0001116844,0.001028151,0.9487824,0.00259471,0.03866382,0.005891379,0.00005145772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3795078,0.004481311,0.5842782,0.004993004,0.0004167935,0.0005339286,0.007619489,0.005881647,0.01228779],"genre_scores_gemma":[0.7971631,0.0008386578,0.1793559,0.0004518618,0.00016199,0.0003958038,0.01936778,0.0007809565,0.001483934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01225194,"threshold_uncertainty_score":0.06479526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2625755630681034,"score_gpt":0.3487654642913454,"score_spread":0.086189901223242,"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."}}