NGM-RAG：基于神经图匹配的检索增强生成
NGM-RAG: Neural Graph Matching based Retrieval-Augmented Generation
浏览论文内容
中文总结 AI 辅助
研究针对传统RAG方法在处理复杂问题时的局限，提出基于神经图匹配的检索增强生成框架NGM-RAG，将图构建、匹配与答案生成统一，结合文本匹配和GNN，采用自适应加权策略，实验证明该模型在多跳问答等任务中性能优越。
中文摘要 AI 辅助
检索增强生成（RAG）通过动态整合外部数据库显著提高了大语言模型提供准确且上下文相关答案的能力。然而，传统RAG方法主要受基于文本的检索策略限制，难以处理需要多跳推理的复杂问题。为解决此局限，我们引入基于神经图匹配的检索增强生成（NGM-RAG），这是一个利用图结构有效捕获和利用关系知识以改进检索和答案生成的新框架。NGM-RAG将图构建、图匹配和答案生成明确整合到统一过程中。在此框架内，我们提出一种结合基于文本匹配与图神经网络（GNN）的神经图匹配方法。通过采用自适应加权策略，NGM-RAG有效整合多种匹配方法以选择最相关的上下文节点信息用于答案生成。在多跳问答和长上下文摘要任务上的实验结果表明，我们的NGM-RAG模型与传统朴素RAG方法以及GraphRAG和LightRAG等先进的图增强方法相比，具有更优性能。
英文摘要
Retrieval-Augmented Generation (RAG) significantly enhances the ability of Large Language Models (LLMs) to provide accurate and contextually relevant answers by dynamically integrating external databases. However, traditional RAG methods are primarily constrained by their reliance on text-based retrieval strategies, which often struggle with complex questions requiring multi-hop reasoning. To address this limitation, we introduce Neural Graph Matching based Retrieval-Augmented Generation (NGM-RAG), a novel framework that leverages graph structures to effectively capture and utilize relational knowledge for improved retrieval and answer generation. NGM-RAG explicitly incorporates graph construction, graph matching, and answer generation into a unified process. Within this framework, we propose a neural graph matching approach that combines text-based matching with Graph Neural Networks (GNNs). By employing an adaptive weighting strategy, NGM-RAG efficiently integrates multiple matching methods to select the most relevant contextual node information for answer generation. Experimental results on multi-hop question answering and long-context summarization tasks demonstrate that our NGM-RAG model achieves superior performance compared to both traditional NaiveRAG methods and state-of-the-art graph-enhanced approaches such as GraphRAG and LightRAG.
