对比知识图谱增强的RAG与传统方法，提升大模型在噪声中的可靠性。
Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative Analysis
- 用知识图谱替代纯文本检索，增强信息一致性
- 在噪声、反事实等场景下，准确率提升12.3%
- 适合构建高可靠知识问答系统的研究者
检索增强生成（RAG）通过引入外部知识源，使大语言模型（LLMs）能突破预训练知识限制，减少事实幻觉并获取新信息。然而，检索结果不一致会负面影响生成质量。为评估RAG系统的鲁棒性，研究提出了检索增强生成基准（RGB）。本文基于RGB语料库，在噪声鲁棒性、信息融合、负例拒绝和反事实鲁棒性四个场景下，对比了RGB基线与基于知识图谱的GraphRAG系统。通过测试三种GraphRAG定制化方案，结果表明其在各项指标上均优于基线，尤其在反事实场景下表现显著提升，为真实世界中构建更可靠的RAG系统提供了设计参考。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) was introduced to enhance the capabilities of Large Language Models (LLMs) beyond their encoded prior knowledge. This is achieved by providing LLMs with an external source of knowledge, which helps reduce factual hallucinations and enables access to new information not available during pretraining. However, inconsistent retrieved information can negatively affect LLM responses. The Retrieval-Augmented Generation Benchmark (RGB) was introduced to evaluate the robustness of RAG systems under such conditions. In this work, we use the RGB corpus to evaluate LLMs in four scenarios: noise robustness, information integration, negative rejection, and counterfactual robustness. We perform a comparative analysis between the RGB RAG baseline and GraphRAG, a knowledge graph based retrieval system. We test three GraphRAG customizations to improve robustness. Results show improvements over the RGB baseline and provide insights for designing more reliable RAG systems for real world scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。