Saved in:
Bibliographic Details
Main Authors: Chen, Siyong, Wen, Jinbo, Kang, Jiawen, Huang, Tenghui, Huang, Xumin, Su, Yuanjia, Pan, Hudan, Zhong, Zishao, Niyato, Dusit, Xie, Shengli, Kim, Dong In
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.21093
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909867203100672
author Chen, Siyong
Wen, Jinbo
Kang, Jiawen
Huang, Tenghui
Huang, Xumin
Su, Yuanjia
Pan, Hudan
Zhong, Zishao
Niyato, Dusit
Xie, Shengli
Kim, Dong In
author_facet Chen, Siyong
Wen, Jinbo
Kang, Jiawen
Huang, Tenghui
Huang, Xumin
Su, Yuanjia
Pan, Hudan
Zhong, Zishao
Niyato, Dusit
Xie, Shengli
Kim, Dong In
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21093
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning
Chen, Siyong
Wen, Jinbo
Kang, Jiawen
Huang, Tenghui
Huang, Xumin
Su, Yuanjia
Pan, Hudan
Zhong, Zishao
Niyato, Dusit
Xie, Shengli
Kim, Dong In
Artificial Intelligence
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.
title MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning
topic Artificial Intelligence
url https://arxiv.org/abs/2510.21093