{"id":"W4414464224","doi":"10.1109/acdsa65407.2025.11166276","title":"Topic Modeling Enhancement using Summaries Generated by LLM Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Technology and Data Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sheridan College","funders":"Research and Development","keywords":"Topic model; Security token; Language model; Document processing; Segmentation; Semantics (computer science); Named entity","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009341983,0.00008102276,0.0001155468,0.0001206665,0.0001556494,0.0000934219,0.000538142,0.00007268681,0.00002160894],"category_scores_gemma":[0.000007547381,0.00007174812,0.00003130302,0.0004706447,0.00002233902,0.000424917,0.0003237445,0.00007118483,0.000005928865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003295834,"about_ca_system_score_gemma":0.0000504808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002565707,"about_ca_topic_score_gemma":0.00003266737,"domain_scores_codex":[0.999284,0.00001769991,0.0001614684,0.0002830461,0.00008438425,0.0001694016],"domain_scores_gemma":[0.9994275,0.00001075514,0.00002111762,0.0004716718,0.00004944348,0.00001951904],"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":[0.000003217644,0.0001019188,0.0001360141,0.00001025202,0.0001332209,0.000003600098,0.00009066668,0.1269506,0.01832614,0.8204765,0.006047896,0.0277199],"study_design_scores_gemma":[0.00007153823,0.000005961158,3.556571e-7,0.000005247633,0.00001216104,2.945924e-7,0.00001432458,0.9473405,0.02624218,0.02561316,0.0006220003,0.00007219786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03664707,0.00045551,0.9599718,0.0008967356,0.00008871029,0.00003978369,0.000002229008,0.0001817616,0.001716398],"genre_scores_gemma":[0.8554453,0.00005369501,0.1413971,0.0008069586,0.000006931611,0.000006265933,0.00001598705,0.000002117403,0.00226568],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8203899,"threshold_uncertainty_score":0.2925803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02606792469033519,"score_gpt":0.2623315734973197,"score_spread":0.2362636488069845,"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."}}