用图神经网络增强复杂问题的文档检索，让模型更懂上下文关联。
Query-Aware Graph Neural Networks for Enhanced Retrieval-Augmented Generation
- 构建带查询感知的动态知识图，捕捉文本块间的语义与顺序关系
- 在多跳问答任务上显著超越传统密集检索方法，提升准确率
- 适合需要跨文档推理的复杂问答场景，如科研或医疗咨询
我们提出一种新型图神经网络架构用于检索增强生成（RAG），通过查询感知注意力机制和可学习评分头，提升复杂多跳问题的检索精度。不同于将文档视为独立实体的传统密集检索方法，本方法为每个问答场景构建知识图，捕获文本片段间的序列与语义关系。引入查询引导的图注意力网络，实现对图中相关部分的动态聚焦。实验表明，该方法在需要多文档推理的复杂问答任务上显著优于标准密集检索器。实现基于PyTorch Geometric，支持图结构数据的高效处理，便于在生产环境中规模化部署。
原文摘要 · Abstract (English)
We present a novel graph neural network (GNN) architecture for retrieval-augmented generation (RAG) that leverages query-aware attention mechanisms and learned scoring heads to improve retrieval accuracy on complex, multi-hop questions. Unlike traditional dense retrieval methods that treat documents as independent entities, our approach constructs per-episode knowledge graphs that capture both sequential and semantic relationships between text chunks. We introduce an Enhanced Graph Attention Network with query-guided pooling that dynamically focuses on relevant parts of the graph based on user queries. Experimental results demonstrate that our approach significantly outperforms standard dense retrievers on complex question answering tasks, particularly for questions requiring multi-document reasoning. Our implementation leverages PyTorch Geometric for efficient processing of graph-structured data, enabling scalable deployment in production retrieval systems
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。