arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.00879cs.CL
收藏

TrustRAG：增强检索增强生成的鲁棒性与可信度

TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation

Imperial College London（伦敦帝国理工学院）；Peking University（北京大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；University College London（伦敦大学学院）

Huichi Zhou, Kin-Hei Lee, Zhonghao Zhan, Yue Chen, Zhenhao Li, Zhaoyang Wang, Hamed Haddadi, Emine Yilmaz

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

TrustRAG提出两阶段防御机制（聚类过滤与自我评估），在检索前过滤恶意内容，以即插即用方式增强RAG的鲁棒性与可信度，实验证明其在检索准确性、效率和攻击抵抗性上均有显著提升。

摘要：

检索增强生成（RAG）通过整合外部知识源来增强大型语言模型（LLMs），从而能够针对用户查询生成更准确且上下文相关的响应。然而，这些系统仍然容易受到语料库投毒攻击，此类攻击可能严重损害LLMs的性能。为应对这一挑战，我们提出了TrustRAG，一个鲁棒的框架，它在内容被检索用于生成之前系统地过滤恶意和无关内容。我们的方法采用两阶段防御机制。第一阶段实施聚类过滤策略以检测潜在的攻击模式。第二阶段采用自我评估过程，利用LLMs的内部能力来检测恶意文档并解决不一致性。TrustRAG提供了一个即插即用、无需训练的模块，可与任何开源或闭源语言模型无缝集成。大量实验表明，TrustRAG在检索准确性、效率和攻击抵抗性方面带来了显著改进。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑