少即是多：为检索增强生成去噪知识图谱
Less is More: Denoising Knowledge Graphs For Retrieval Augmented Generation
AI总结：
针对LLM构建知识图谱含噪声的问题，提出DEG-RAG框架，通过实体解析和三元组反思去噪，生成更紧凑高质量图谱，显著提升多种图RAG变体的问答性能。
摘要：
检索增强生成（RAG）系统使大型语言模型（LLMs）能够在生成过程中即时访问相关信息，在解决幻觉、事实不准确和知识截止等常见LLM挑战方面展现出卓越性能。基于图的RAG通过引入知识图谱（KGs）进一步扩展了这一范式，利用丰富、结构化的连接来实现更精确和更具推理性的响应。然而，一个关键挑战是，大多数基于图的RAG系统依赖LLM进行自动化知识图谱构建，这往往会产生带有冗余实体和不可靠关系的噪声知识图谱。这种噪声会降低检索和生成性能，同时增加计算成本。至关重要的是，当前研究并未全面解决LLM生成知识图谱的去噪问题。在本文中，我们提出了用于检索增强生成的去噪知识图谱（DEG-RAG）框架，该框架通过以下技术应对这些挑战：（1）实体解析，消除冗余实体，以及（2）三元组反思，移除错误关系。这些技术共同产生更紧凑、更高质量的知识图谱，其性能显著优于未处理的对应版本。除方法外，我们还对LLM生成知识图谱的实体解析进行了系统评估，考察了不同的分块策略、嵌入选择、相似度度量和实体合并技术。据我们所知，这是对LLM生成知识图谱中实体解析的首次全面探索。我们的实验表明，这种直接的方法不仅大幅减小了图谱规模，而且在多种流行的基于图的RAG变体中持续提升了问答性能。
英文摘要：
Retrieval-Augmented Generation (RAG) systems enable large language models (LLMs) instant access to relevant information for the generative process, demonstrating their superior performance in addressing common LLM challenges such as hallucination, factual inaccuracy, and the knowledge cutoff. Graph-based RAG further extends this paradigm by incorporating knowledge graphs (KGs) to leverage rich, structured connections for more precise and inferential responses. A critical challenge, however, is that most Graph-based RAG systems rely on LLMs for automated KG construction, often yielding noisy KGs with redundant entities and unreliable relationships. This noise degrades retrieval and generation performance while also increasing computational cost. Crucially, current research does not comprehensively address the denoising problem for LLM-generated KGs. In this paper, we introduce DEnoised knowledge Graphs for Retrieval Augmented Generation (DEG-RAG), a framework that addresses these challenges through: (1) entity resolution, which eliminates redundant entities, and (2) triple reflection, which removes erroneous relations. Together, these techniques yield more compact, higher-quality KGs that significantly outperform their unprocessed counterparts. Beyond the methods, we conduct a systematic evaluation of entity resolution for LLM-generated KGs, examining different blocking strategies, embedding choices, similarity metrics, and entity merging techniques. To the best of our knowledge, this is the first comprehensive exploration of entity resolution in LLM-generated KGs. Our experiments demonstrate that this straightforward approach not only drastically reduces graph size but also consistently improves question answering performance across diverse popular Graph-based RAG variants.
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。
