{"id":"W7125644766","doi":"10.1109/cascon66301.2025.00081","title":"Towards Improving the Reliability of LLMs in Requirements Engineering with Structured Confidence and Tag Governance","year":2025,"lang":"","type":"article","venue":"","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Reliability (semiconductor); Corporate governance; Risk management; Risk assessment; Process (computing); Requirements analysis","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":[0.02850843,0.0007732862,0.0009372209,0.002050224,0.0007241361,0.004729532,0.002623769,0.002364799,0.001962178],"category_scores_gemma":[0.1547347,0.0009529564,0.00113431,0.001184081,0.00275467,0.008805697,0.005614717,0.004322541,0.0009428585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001952562,"about_ca_system_score_gemma":0.004416545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002440542,"about_ca_topic_score_gemma":0.002892766,"domain_scores_codex":[0.9618032,0.02309576,0.002199892,0.001938678,0.009443603,0.001518787],"domain_scores_gemma":[0.8370336,0.07425433,0.01306342,0.05393884,0.02029562,0.001414203],"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":[0.0006945106,0.001012888,0.02954603,0.000744459,0.000289901,0.0003604355,0.003622224,0.2351106,0.03951988,0.1747742,0.00294785,0.5113771],"study_design_scores_gemma":[0.00008698193,0.0005883609,0.003325596,0.0003042553,0.0001476687,0.0001567011,0.0007335473,0.8346134,0.02791114,0.1275404,0.004527394,0.00006444116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08037263,0.0002800404,0.9128786,0.00132301,0.00003619624,0.000149426,0.00003904092,0.00177208,0.003148943],"genre_scores_gemma":[0.6939502,0.0001607833,0.3034976,0.0003084495,0.00004088324,0.0001538314,0.0001449878,0.0003810288,0.001362132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02850843,"threshold_uncertainty_score":0.1507688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00842075722685158,"score_gpt":0.2434121089369344,"score_spread":0.2349913517100828,"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."}}