{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002336644,0.002297432,0.001097694,0.0007366138,0.0005084518,0.002087526,0.003011554,0.002106812,0.004233971],"category_scores_gemma":[0.01120297,0.0008917837,0.001511112,0.0006734619,0.001144921,0.004133972,0.002696943,0.00407397,0.002066385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001336263,"about_ca_system_score_gemma":0.002207783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006849903,"about_ca_topic_score_gemma":0.01419415,"domain_scores_codex":[0.9988391,0.0005077556,0.00006637806,0.0003264947,0.0001830879,0.00007725668],"domain_scores_gemma":[0.9975769,0.001591584,0.00009573384,0.0004511578,0.000198641,0.00008601436],"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":[0.0003505432,0.0002747052,0.001925472,0.0006371443,0.0001869252,0.0003374876,0.0002391607,0.7545506,0.005833295,0.01341039,0.02001766,0.2022366],"study_design_scores_gemma":[0.00002930408,0.0000553537,0.00007693849,0.00001472353,0.00001215791,0.0000312877,0.00002600604,0.9901983,0.001309288,0.00623797,0.001998634,0.00001003637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1049903,0.002495212,0.8443766,0.002103084,0.0004601242,0.0003177679,0.001336191,0.03458621,0.009334491],"genre_scores_gemma":[0.4636535,0.0006016399,0.5223021,0.001530127,0.0001414951,0.0005652437,0.003718211,0.002621818,0.004865865],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006849903,"threshold_uncertainty_score":0.01416409,"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."}}