{"id":"W4411488587","doi":"10.1145/3744920","title":"On the Utility of Domain Modeling Assistance with Large Language Models","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Université de Montréal","funders":"","keywords":"Computer science; Modeling language; Domain (mathematical analysis); Usability; Software engineering; Domain analysis; Abstraction; Domain-specific language; Process (computing); Model-driven architecture; Context (archaeology); Subject-matter expert; Domain model; Software; Domain engineering; Human–computer interaction; Software development; Data science; Artificial intelligence; Domain knowledge; Programming language; Component-based software engineering; Software construction","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":[0.0115558,0.001355659,0.0005168503,0.00138241,0.0008504685,0.002585409,0.001822605,0.001993002,0.003151029],"category_scores_gemma":[0.09908579,0.0006478396,0.0005574376,0.000886393,0.001109906,0.007871268,0.002897169,0.002034991,0.0009415102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009474091,"about_ca_system_score_gemma":0.001488093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006923289,"about_ca_topic_score_gemma":0.008747774,"domain_scores_codex":[0.9906313,0.006776527,0.0003140246,0.0009797461,0.001134899,0.0001635427],"domain_scores_gemma":[0.8425185,0.1450806,0.001469428,0.006691752,0.003512075,0.0007277401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002892479,0.002324549,0.01533104,0.001302415,0.0002718401,0.0006448142,0.005812002,0.1696058,0.03312735,0.01472881,0.007141198,0.7468178],"study_design_scores_gemma":[0.000156481,0.001000853,0.003257342,0.0001765061,0.0001084225,0.0003173107,0.001188253,0.9523172,0.02074123,0.01293355,0.007708208,0.00009473367],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.450648,0.001348365,0.5214788,0.002352057,0.0001034509,0.000563958,0.0005417783,0.01125089,0.01171274],"genre_scores_gemma":[0.7524036,0.0004047554,0.2443715,0.0002659733,0.0000251793,0.0001374407,0.0004480505,0.0004936112,0.001449787],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0115558,"threshold_uncertainty_score":0.06111366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06253040734009754,"score_gpt":0.3178245270606738,"score_spread":0.2552941197205763,"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."}}