{"id":"W4401783591","doi":"10.1080/03155986.2024.2388452","title":"LM4OPT: Unveiling the potential of Large Language Models in formulating mathematical optimization problems","year":2024,"lang":"en","type":"article","venue":"INFOR Information Systems and Operational Research","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Comprehension; Task (project management); Computer science; Shot (pellet); Natural language processing; Artificial intelligence; Machine learning; Engineering; Chemistry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.003162856,0.00006869964,0.0001028351,0.0003152069,0.0001792724,0.0008815592,0.0002595707,0.00006136311,0.000007977921],"category_scores_gemma":[0.0001226829,0.00004658383,0.00002395728,0.0004265826,0.00002765815,0.003667435,0.0001847093,0.0002105446,0.00001264957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005097066,"about_ca_system_score_gemma":0.0001712022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001084294,"about_ca_topic_score_gemma":0.000005159927,"domain_scores_codex":[0.9982522,0.00007069664,0.0006044022,0.0001049139,0.000758699,0.0002091406],"domain_scores_gemma":[0.999222,0.0002036664,0.00004830579,0.0001847223,0.0003046149,0.0000367387],"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":[0.000001145196,0.000003396108,0.00000819176,0.0001668937,0.000003241563,4.469593e-7,0.005230573,0.5801072,0.00002388438,0.4130022,0.00001524792,0.001437663],"study_design_scores_gemma":[0.0001526861,0.00001545,0.00001885799,0.0001933128,7.596725e-7,0.00001906812,0.001724317,0.9958665,0.00002540701,0.00168819,0.0002446685,0.00005082672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01741434,0.0003017365,0.977677,0.0003610173,0.00009488775,0.0005238153,0.000008477577,0.00003389596,0.003584831],"genre_scores_gemma":[0.989857,0.00001981556,0.009860132,0.00003267561,0.00004606223,0.00007050986,0.00001955038,0.00000354318,0.00009074221],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9724426,"threshold_uncertainty_score":0.8500896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0502706093629151,"score_gpt":0.3448931668239208,"score_spread":0.2946225574610057,"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."}}