{"id":"W4389606799","doi":"10.1109/models58315.2023.00037","title":"Automated Domain Modeling with Large Language Models: A Comparative Study","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Universidad de Murcia","keywords":"Domain (mathematical analysis); Computer science; Set (abstract data type); Modeling language; Domain-specific language; Subject-matter expert; Domain model; Class (philosophy); Domain analysis; Software; Domain knowledge; Natural language processing; Software engineering; Data science; Artificial intelligence; Programming language; Software development; Expert system","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":[0.0247071,0.001277801,0.001026937,0.005391276,0.000836237,0.003545573,0.002608192,0.001353823,0.001850988],"category_scores_gemma":[0.1018313,0.00063272,0.001672565,0.005391183,0.001075835,0.006956459,0.003137084,0.001775678,0.0005544955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002785248,"about_ca_system_score_gemma":0.002350173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006263711,"about_ca_topic_score_gemma":0.006233802,"domain_scores_codex":[0.9754625,0.01751067,0.001260872,0.001440544,0.004029097,0.0002963078],"domain_scores_gemma":[0.7774536,0.1926797,0.004517328,0.01635529,0.008138712,0.000855406],"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":[0.001676598,0.002100773,0.0512408,0.002349116,0.001078542,0.0006751718,0.007605664,0.2242763,0.004348772,0.02264874,0.009738463,0.6722611],"study_design_scores_gemma":[0.0003029846,0.001156056,0.02714935,0.0004829723,0.0005830377,0.0005525776,0.003227594,0.9124775,0.00723313,0.01768387,0.02898519,0.0001657987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7606074,0.007834646,0.1996242,0.002435963,0.0001353967,0.0009059682,0.002185047,0.007399253,0.0188721],"genre_scores_gemma":[0.8167381,0.002589498,0.1736626,0.000264412,0.00006388422,0.0004189164,0.004470251,0.0006822904,0.001110013],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0247071,"threshold_uncertainty_score":0.1306652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05186317309112483,"score_gpt":0.3344085128492332,"score_spread":0.2825453397581084,"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."}}