MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Pingyu, Gao, Daiheng, Tang, Jing, Chen, Huimin, Zhou, Wenbo, Zhang, Weiming, Yu, Nenghai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908273504944128
author Wu, Pingyu
Gao, Daiheng
Tang, Jing
Chen, Huimin
Zhou, Wenbo
Zhang, Weiming
Yu, Nenghai
author_facet Wu, Pingyu
Gao, Daiheng
Tang, Jing
Chen, Huimin
Zhou, Wenbo
Zhang, Weiming
Yu, Nenghai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_13563
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG
Wu, Pingyu
Gao, Daiheng
Tang, Jing
Chen, Huimin
Zhou, Wenbo
Zhang, Weiming
Yu, Nenghai
Computation and Language
Artificial Intelligence
Information Retrieval
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.
title MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2503.13563