通过分类和重写问题，提升RAG的检索与生成效果
PreQRAG -- Classify and Rewrite for Enhanced RAG
- 根据问题类型分单文档或多文档，分别处理
- 在LiveRAG挑战中获第二名，显著提升性能
- 适合需要精准问答的系统开发人员使用
本文介绍了UDInfo团队在SIGIR 2025 LiveRAG挑战中的提交方案。我们提出PreQRAG，一种基于检索增强生成（RAG）的架构，通过针对性的问题预处理提升检索与生成质量。该架构首先将输入问题分类为单文档或多文档类型：针对单文档问题，采用重写技术提高检索精度与生成相关性；针对多文档问题，则将复杂查询分解为聚焦的子问题，使下游组件更高效处理。这种基于问题类型的感知策略有效提升了RAG性能。在LiveRAG挑战数据集上的实验表明，PreQRAG在第二轮会话中取得初步第二名的成绩。
原文摘要 · Abstract (English)
This paper presents the submission of the UDInfo team to the SIGIR 2025 LiveRAG Challenge. We introduce PreQRAG, a Retrieval Augmented Generation (RAG) architecture designed to improve retrieval and generation quality through targeted question preprocessing. PreQRAG incorporates a pipeline that first classifies each input question as either single-document or multi-document type. For single-document questions, we employ question rewriting techniques to improve retrieval precision and generation relevance. For multi-document questions, we decompose complex queries into focused sub-questions that can be processed more effectively by downstream components. This classification and rewriting strategy improves the RAG performance. Experimental evaluation of the LiveRAG Challenge dataset demonstrates the effectiveness of our question-type-aware architecture, with PreQRAG achieving the preliminary second place in Session 2 of the LiveRAG challenge.
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。