{"ID":2850432,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.21093","arxiv_id":"2510.21093","title":"MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning","abstract":"Recently, large models have shown significant potential for smart healthcare. However, the deployment of Large Vision-Language Models (LVLMs) for clinical services is currently hindered by three critical challenges: a tendency to hallucinate answers not grounded in visual evidence, the inefficiency of fixed-depth reasoning, and the difficulty of multi-institutional collaboration. To address these challenges, in this paper, we develop MedAlign, a novel framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA). Specifically, we first propose a multimodal Direct Preference Optimization (mDPO) objective to explicitly align preference learning with visual context. We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM (i.e., an expert), thereby mitigating hallucinations in LVLMs. To achieve adaptive reasoning and facilitate multi-institutional collaboration, we propose a federated governance mechanism, where the selected expert, fine-tuned on clinical datasets based on mDPO, locally performs iterative Chain-of-Thought (CoT) reasoning via the local meta-cognitive uncertainty estimator. Extensive experiments on three representative Med-VQA datasets demonstrate that MedAlign achieves state-of-the-art performance, outperforming strong retrieval-augmented baselines by up to $11.85\\%$ in F1-score, and simultaneously reducing the average reasoning length by $51.60\\%$ compared with fixed-depth CoT approaches.","short_abstract":"Recently, large models have shown significant potential for smart healthcare. However, the deployment of Large Vision-Language Models (LVLMs) for clinical services is currently hindered by three critical challenges: a tendency to hallucinate answers not grounded in visual evidence, the inefficiency of fixed-depth reaso...","url_abs":"https://arxiv.org/abs/2510.21093","url_pdf":"https://arxiv.org/pdf/2510.21093v1","authors":"[\"Siyong Chen\",\"Jinbo Wen\",\"Jiawen Kang\",\"Tenghui Huang\",\"Xumin Huang\",\"Yuanjia Su\",\"Hudan Pan\",\"Zishao Zhong\",\"Dusit Niyato\",\"Shengli Xie\",\"Dong In Kim\"]","published":"2025-10-24T02:11:05Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Language Model\"]","has_code":false}