ReliableRAG：通过可靠性引导推理链对抗检索增强生成中的错误信息

中文摘要 AI 辅助

检索增强生成（Retrieval-Augmented Generation，RAG）架构通过将外部信息整合进大型语言模型（Large Language Models，LLMs），已成为问答（Question Answering，QA）领域的强大技术。然而，新闻和社交媒体中的虚假、不准确及误导性信息，对现实世界的RAG系统构成了严峻挑战，尤其是在多跳问答场景中，即使检索到的文档中仅有一段具有欺骗性的错误信息，也可能误导复杂的多步推理。现有方法主要依赖隐式对齐或显式调控，但它们评估细粒度信息可靠性的能力有限，易受那些在语义上与问题相关但事实上错误的欺骗性错误信息影响，进而生成错误答案。为解决这一局限，我们提出ReliableRAG，据我们所知，这是首个通过细粒度评估单个三元组来缓解多跳问答中欺骗性错误信息的可靠性驱动框架。ReliableRAG首先从源文档中提取信息片段，并将其表示为结构化三元组；接着，它结合查询-三元组语义相关性与三元组可信度来量化三元组可靠性，仅保留排名前K的可靠且非冗余三元组；基于这些优化后的三元组，ReliableRAG自回归构建鲁棒推理链，以整合可信证据并过滤欺骗性错误信息，生成忠实于可靠信息的准确答案。在三个多跳问答数据集上的实验表明，ReliableRAG的性能优于现有方法，在注入欺骗性错误信息的情况下，显著提升了RAG系统的事实可靠性与鲁棒性。

英文摘要

Retrieval-Augmented Generation (RAG) has emerged as a powerful architecture for Question Answering (QA) by integrating external information into Large Language Models (LLMs). However, false, inaccurate, and misleading information in news and social media poses a serious challenge to real-world RAG systems, especially in multi-hop QA, where complex multi-step reasoning can be misled by even a single deceptive misinformation segment in the retrieved documents. Existing approaches mainly rely on implicit alignment or explicit regulation, but their limited ability to assess fine-grained information reliability makes them vulnerable to deceptive misinformation that is semantically relevant to the question yet factually incorrect, leading to erroneous answers. To address this limitation, we propose ReliableRAG, which, to the best of our knowledge, is the first reliability-driven framework that mitigates deceptive misinformation in multi-hop QA through fine-grained evaluation of individual triples. ReliableRAG first extracts information segments from source documents and represents them as structured triples. It then quantifies triple reliability by combining query-triple semantic relevance with triple credibility, retaining only the top-$K$ reliable and non-redundant triples. Based on these refined triples, ReliableRAG autoregressively constructs robust reasoning chains to consolidate trustworthy evidence and filter deceptive misinformation, producing accurate answers faithful to reliable information. Experiments on three multi-hop QA datasets show that ReliableRAG outperforms existing methods, substantially improving the factual reliability and robustness of RAG systems under deceptive misinformation injection.

发表机构

• College of Software, Jilin University（吉林大学软件学院）
• College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）
• Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院 教育部符号计算与知识工程重点实验室）
• College of Computer Science and Technology, Dalian University of Technology（大连理工大学计算机科学与技术学院）
• National University of Singapore（新加坡国立大学）
• School of Computer Science, Zhuhai College of Science and Technology（珠海科技学院计算机学院）

机构由 AI 辅助整理，请以论文原文为准。