解决多跳问答中关键实体丢失导致检索失败的问题
Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering
- 分步重构子问题，补全缺失实体并从句图检索相关句子
- 在三个数据集上提升准确率，对三种大模型均有效
- 适合需要精准推理链的复杂问答任务
本文识别出检索增强型多跳问答中的关键问题——‘丢失在检索中’：大语言模型在分解子问题时遗漏关键实体。这一问题严重降低检索效果，打断推理链，导致错误答案。为此，我们提出渐进式检索与重写方法 ChainRAG，通过逐个处理子问题，补全缺失关键实体，并从句子图中检索相关句子以生成答案。每一步基于前一步结果，形成连贯链条，最终整合所有检索句子和子问题答案，生成完整回答。我们在 MuSiQue、2Wiki、HotpotQA 三个多跳问答数据集上，使用 GPT4o-mini、Qwen2.5-72B、GLM-4-Plus 三种大模型进行评估。实证结果表明，ChainRAG 在有效性和效率上均持续优于基线方法。
原文摘要 · Abstract (English)
In this paper, we identify a critical problem, "lost-in-retrieval", in retrieval-augmented multi-hop question answering (QA): the key entities are missed in LLMs' sub-question decomposition. "Lost-in-retrieval" significantly degrades the retrieval performance, which disrupts the reasoning chain and leads to the incorrect answers. To resolve this problem, we propose a progressive retrieval and rewriting method, namely ChainRAG, which sequentially handles each sub-question by completing missing key entities and retrieving relevant sentences from a sentence graph for answer generation. Each step in our retrieval and rewriting process builds upon the previous one, creating a seamless chain that leads to accurate retrieval and answers. Finally, all retrieved sentences and sub-question answers are integrated to generate a comprehensive answer to the original question. We evaluate ChainRAG on three multi-hop QA datasets - MuSiQue, 2Wiki, and HotpotQA - using three large language models: GPT4o-mini, Qwen2.5-72B, and GLM-4-Plus. Empirical results demonstrate that ChainRAG consistently outperforms baselines in both effectiveness and efficiency.
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。