MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation 文章

ArXiv CS.CV2026-06-17NEWSen作者: Zehang Wei, Jiaxin Dai, Jiamin Yan, Xiang Xiang

详细信息

来源站点
ArXiv CS.CV
作者
Zehang Wei, Jiaxin Dai, Jiamin Yan, Xiang Xiang
文章类型
NEWS
语言
en
发布日期
2026-06-17

摘要

arXiv:2606.17449v1 Announce Type: cross Abstract: While Multimodal Retrieval-Augmented Generation (M-RAG) enhances Large Vision-Language Models, it remains highly susceptible to cross-modal hallucinations, causal fabrications, and sycophancy. Furthermore, existing mitigation pipelines often face an intervention paradox: static rules tend to unnecessarily disrupt accurate generations, whereas leaving the multi-modal reasoning completely unguided allows existing mismatches to cascade into severe logical fabrications. To quantify and mitigate these hallucinations, we propose a Multi-Agent system, MODE-RAG, driven by Variational Free Energy (VFE) and internal attention states to dynamically gate interventions. High-risk queries are routed to five stage-specific agents, integrating Monte Carlo Tree Search (MCTS) for rigorous causal derivation and logit perturbations to penalize sycophancy.