BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering

ArXi:2605.17435v1 Announce Type: new Biomedical question answering often requires decisions from retrieved literature whose relevance, quality, and for candidate answers are uneven. Most retrieval-augmented large language model (LLM) methods feed this literature to the model as flat text, leaving evidence reliability and remaining uncertainty largely implicit. We propose BELIEF, a structured evidence modeling and uncertainty-aware fusion framework for closed-set biomedical question answering.