Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhou, Huichi, Lee, Kin-Hei, Zhan, Zhonghao, Chen, Yue, Li, Zhenhao, Wang, Zhaoyang, Haddadi, Hamed, Yilmaz, Emine
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2501.00879
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910963732578304
author Zhou, Huichi
Lee, Kin-Hei
Zhan, Zhonghao
Chen, Yue
Li, Zhenhao
Wang, Zhaoyang
Haddadi, Hamed
Yilmaz, Emine
author_facet Zhou, Huichi
Lee, Kin-Hei
Zhan, Zhonghao
Chen, Yue
Li, Zhenhao
Wang, Zhaoyang
Haddadi, Hamed
Yilmaz, Emine
contents Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user queries. These systems, however, remain susceptible to corpus poisoning attacks, which can severely impair the performance of LLMs. To address this challenge, we propose TrustRAG, a robust framework that systematically filters malicious and irrelevant content before it is retrieved for generation. Our approach employs a two-stage defense mechanism. The first stage implements a cluster filtering strategy to detect potential attack patterns. The second stage employs a self-assessment process that harnesses the internal capabilities of LLMs to detect malicious documents and resolve inconsistencies. TrustRAG provides a plug-and-play, training-free module that integrates seamlessly with any open- or closed-source language model. Extensive experiments demonstrate that TrustRAG delivers substantial improvements in retrieval accuracy, efficiency, and attack resistance.
format Preprint
id arxiv_https___arxiv_org_abs_2501_00879
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation
Zhou, Huichi
Lee, Kin-Hei
Zhan, Zhonghao
Chen, Yue
Li, Zhenhao
Wang, Zhaoyang
Haddadi, Hamed
Yilmaz, Emine
Computation and Language
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user queries. These systems, however, remain susceptible to corpus poisoning attacks, which can severely impair the performance of LLMs. To address this challenge, we propose TrustRAG, a robust framework that systematically filters malicious and irrelevant content before it is retrieved for generation. Our approach employs a two-stage defense mechanism. The first stage implements a cluster filtering strategy to detect potential attack patterns. The second stage employs a self-assessment process that harnesses the internal capabilities of LLMs to detect malicious documents and resolve inconsistencies. TrustRAG provides a plug-and-play, training-free module that integrates seamlessly with any open- or closed-source language model. Extensive experiments demonstrate that TrustRAG delivers substantial improvements in retrieval accuracy, efficiency, and attack resistance.
title TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation
topic Computation and Language
url https://arxiv.org/abs/2501.00879