优化问答语义空间，提升多跳问答的准确与效率
Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering
- 将复杂问题拆解为细粒度子问题并建模依赖关系
- 在多个基准上超越现有方法，跨域表现更优
- 动态检索匹配，兼顾精度与计算效率，适合复杂问答场景
检索增强生成（RAG）常被集成到大语言模型中以缓解幻觉和知识过时问题。然而，传统的一步式检索-阅读方法在多跳问答任务中存在语义不匹配及子问题间依赖处理成本高的问题。本文提出面向动态检索增强型多跳问答的问答语义空间优化方法（Q-DREAM）。该方法包含三个核心模块：(1) 问答分解模块（QDM），将多跳问题分解为细粒度子问题；(2) 子问题依赖优化模块（SDOM），建模子问题间的相互依赖关系以增强理解；(3) 动态文档检索模块（DPRM），通过优化语义嵌入实现子问题与相关段落的对齐。在多个基准上的实验结果表明，Q-DREAM显著优于现有RAG方法，在域内与域外设置下均达到领先性能。值得注意的是，相比近期基线，Q-DREAM在保持高准确率的同时提升了检索效率。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) is usually integrated into large language models (LLMs) to mitigate hallucinations and knowledge obsolescence. Whereas,conventional one-step retrieve-and-read methods are insufficient for multi-hop question answering, facing challenges of retrieval semantic mismatching and the high cost in handling interdependent subquestions. In this paper, we propose Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering (Q-DREAM). Q-DREAM consists of three key modules: (1) the Question Decomposition Module (QDM), which decomposes multi-hop questions into fine-grained subquestions; (2) the Subquestion Dependency Optimizer Module (SDOM), which models the interdependent relations of subquestions for better understanding; and (3) the Dynamic Passage Retrieval Module (DPRM), which aligns subquestions with relevant passages by optimizing the semantic embeddings. Experimental results across various benchmarks demonstrate that Q-DREAM significantly outperforms existing RAG methods, achieving state-of-the-art performance in both in-domain and out-of-domain settings. Notably, Q-DREAM also improves retrieval efficiency while maintaining high accuracy compared with recent baselines.
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。