{"id":"W4408222036","doi":"10.2139/ssrn.5170458","title":"Large Language Models for Conceptual Modeling: Assessment and Application Potential","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Conceptual model; Natural language processing","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":[0.01605377,0.001342116,0.002006343,0.003028422,0.001359709,0.006657219,0.003401731,0.002216659,0.007302892],"category_scores_gemma":[0.07960591,0.001191613,0.002847071,0.003726912,0.001742139,0.01136636,0.002734139,0.004110614,0.00180413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003230993,"about_ca_system_score_gemma":0.003359721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01004148,"about_ca_topic_score_gemma":0.01146771,"domain_scores_codex":[0.9900203,0.007920815,0.0002684837,0.0006690045,0.0009582495,0.0001631891],"domain_scores_gemma":[0.8481413,0.1383699,0.001760446,0.006717986,0.003608428,0.001401949],"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":[0.0008123213,0.0005709507,0.006518318,0.0008462028,0.0008097739,0.0001907151,0.001360927,0.3038881,0.001510025,0.5021384,0.01429872,0.1670556],"study_design_scores_gemma":[0.00004330525,0.00004315477,0.0003047498,0.00004812546,0.00007143964,0.00003626508,0.0001037022,0.7705713,0.0002543454,0.2253513,0.003148028,0.00002424354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02067673,0.00166496,0.9694799,0.002539612,0.0001046551,0.000141492,0.0008564458,0.001837434,0.002698748],"genre_scores_gemma":[0.4109209,0.00283375,0.5767316,0.0006372616,0.0005881792,0.00091681,0.003031502,0.001032723,0.00330732],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01605377,"threshold_uncertainty_score":0.08490151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01598825906235291,"score_gpt":0.30250119961842,"score_spread":0.2865129405560671,"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."}}