{"id":"W4411507372","doi":"10.1016/j.datak.2025.102480","title":"Large language models for conceptual modeling: Assessment and application potential","year":2025,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Fundação para a Ciência e a Tecnologia; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01213449,0.0008921156,0.001133527,0.003050379,0.001217599,0.005642711,0.002953382,0.001848339,0.005561384],"category_scores_gemma":[0.06222919,0.0008553507,0.001807612,0.003184738,0.001463775,0.01281432,0.002199812,0.002262287,0.001059254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003368768,"about_ca_system_score_gemma":0.003464676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01013379,"about_ca_topic_score_gemma":0.01280363,"domain_scores_codex":[0.9933918,0.004382949,0.0002680265,0.0004454928,0.001399031,0.0001128512],"domain_scores_gemma":[0.9219537,0.06500807,0.001323809,0.006596714,0.004282078,0.0008356578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009196377,0.0008963728,0.009566668,0.0009416882,0.0007076706,0.0002477349,0.001305461,0.2486024,0.002578216,0.502632,0.01408407,0.2175181],"study_design_scores_gemma":[0.00007220844,0.00008645376,0.0006325508,0.0001315609,0.0001482681,0.00008062735,0.0002610312,0.7609238,0.001050743,0.2284565,0.008116593,0.00003972879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05721329,0.002398024,0.925136,0.003983676,0.0001655694,0.0003011371,0.00191638,0.002755243,0.006130578],"genre_scores_gemma":[0.4411584,0.002254696,0.5487381,0.0004827335,0.0002037658,0.0007587356,0.003551555,0.0007204637,0.002131542],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01213449,"threshold_uncertainty_score":0.06417412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02950059442361724,"score_gpt":0.3180202898758975,"score_spread":0.2885196954522802,"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."}}