用生成的问题嵌入提升多跳问答的检索精度
Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generation
- 将复杂问题分解为可回答的小问题，明确知识切入点
- 用文档生成可回答问题并做嵌入检索，准确率显著提升
- 适合需要深度推理的问答场景，尤其在长文本中表现优异
我们提出一种面向多跳问答的新型检索增强生成（RAG）框架。首先，利用大语言模型（LLM）将复杂的多跳问题分解为一系列单跳子问题，以引导文档检索，降低多跳查询的歧义性。其次，不直接对原始或分块文档进行嵌入，而是使用Qwen3-8B从每个文档块生成可回答的问题，再对这些生成的问题进行嵌入，并通过问题-问题相似度检索相关文档块。推理时，将检索到的文档块与原问题一同输入RAG流程。我们在LongBench的三个多跳问答数据集（MuSiQue、2WikiMultiHopQA、HotpotQA）上进行评估，结果表明该方法优于基线系统。研究展示了使用可回答问题嵌入在RAG中的优势，以及基于LLM的查询分解在多跳场景下的有效性。
原文摘要 · Abstract (English)
We introduce a novel retrieval-augmented generation (RAG) framework tailored for multihop question answering. First, our system uses large language model (LLM) to decompose complex multihop questions into a sequence of single-hop subquestions that guide document retrieval. This decomposition mitigates the ambiguity inherent in multi-hop queries by clearly targeting distinct knowledge facets. Second, instead of embedding raw or chunked documents directly, we generate answerable questions from each document chunk using Qwen3-8B, embed these generated questions, and retrieve relevant chunks via question-question embedding similarity. During inference, the retrieved chunks are then fed along with the original question into the RAG pipeline. We evaluate on three multihop question datasets (MuSiQue, 2WikiMultiHopQa, HotpotQA) from LongBench. Our method improves RAG performacne compared to baseline systems. Our contributions highlight the benefits of using answerable-question embeddings for RAG, and the effectiveness of LLM-based query decomposition for multihop 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。