Retrieval-Augmented Generation (RAG) improves Large Language Models (LLMs) by using external knowledge, but it struggles with precise entity information retrieval. In this paper, we proposed MES-RAG framework, which enhances entity-specific query handling and provides accurate, secure, and consistent responses. MES-RAG introduces proactive security measures that ensure system integrity by applying protections prior to data access. Additionally, the system supports real-time multi-modal outputs, including text, images, audio, and video, seamlessly integrating into existing RAG architectures. Experimental results demonstrate that MES-RAG significantly improves both accuracy and recall, highlighting its effectiveness in advancing the security and utility of question-answering, increasing accuracy to 0.83 (+0.25) on targeted task. Our code and data are available at https://github.com/wpydcr/MES-RAG.
@article{arxiv.2503.13563,
title = {MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG},
author = {Pingyu Wu and Daiheng Gao and Jing Tang and Huimin Chen and Wenbo Zhou and Weiming Zhang and Nenghai Yu},
journal= {arXiv preprint arXiv:2503.13563},
year = {2025}
}