{"ID":2839212,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.16625","arxiv_id":"2511.16625","title":"MedBayes-Lite: Bayesian Uncertainty Quantification for Safe Clinical Decision Support","abstract":"We propose MedBayes-Lite, a lightweight Bayesian enhancement for transformer-based clinical language models that improves reliability through uncertainty-aware prediction. The framework operates without retraining, architectural modification, or additional trainable parameters, and integrates three components: Bayesian Embedding Calibration via Monte Carlo dropout, Uncertainty-Weighted Attention for reliability-aware token aggregation, and Confidence-Guided Decision Shaping for abstention under uncertainty. Across MedQA, PubMedQA, and MIMIC-III, MedBayes-Lite improves calibration and trustworthiness, reducing overconfidence by 32--48\\%. In simulated clinical settings, it further supports safer decision-making by flagging uncertain predictions for human review, particularly under distribution shift. For closed API models, the framework remains applicable through sampling-based predictive uncertainty and confidence-guided abstention, while full embedding- and attention-level uncertainty propagation is evaluated on open-weight transformer models.","short_abstract":"We propose MedBayes-Lite, a lightweight Bayesian enhancement for transformer-based clinical language models that improves reliability through uncertainty-aware prediction. The framework operates without retraining, architectural modification, or additional trainable parameters, and integrates three components: Bayesian...","url_abs":"https://arxiv.org/abs/2511.16625","url_pdf":"https://arxiv.org/pdf/2511.16625v2","authors":"[\"Elias Hossain\",\"Md Mehedi Hasan Nipu\",\"Maleeha Sheikh\",\"Rajib Rana\",\"Subash Neupane\",\"Niloofar Yousefi\"]","published":"2025-11-20T18:33:12Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Transformer\",\"Language Model\"]","has_code":false}