树状推理：改进多跳问题回答的检索增强生成
Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
AI总结：
RT-RAG通过构建推理树来提升多跳问题回答的准确性和一致性，实验结果显示其在F1和EM指标上均优于现有方法。
摘要：
检索增强生成（RAG）在增强大型语言模型（LLMs）以处理复杂多跳问题回答（QA）方面已显示出显著的有效性。对于多跳QA任务，当前的迭代方法主要依赖LLMs自行引导和规划多步探索路径，导致在保持步骤间推理一致性方面存在重大挑战，特别是在查询分解不准确和错误传播方面。为了解决这些问题，我们引入了推理树引导RAG（RT-RAG），一种新的层次化框架用于复杂多跳QA。RT-RAG系统地将多跳问题分解为显式的推理树，通过结构化的实体分析和基于共识的树选择来最小化不准确的分解，明确区分核心查询、已知实体和未知实体。随后，一种自底向上的遍历策略利用迭代查询重写和细化来收集高质量的证据，从而减轻错误传播。全面的实验表明，RT-RAG在F1和EM指标上分别比最先进的方法高出7.0%和6.0%，证明了RT-RAG在复杂多跳QA中的有效性。
英文摘要：
Retrieval-Augmented Generation (RAG) has demonstrated significant effectiveness in enhancing large language models (LLMs) for complex multi-hop question answering (QA). For multi-hop QA tasks, current iterative approaches predominantly rely on LLMs to self-guide and plan multi-step exploration paths during retrieval, leading to substantial challenges in maintaining reasoning coherence across steps from inaccurate query decomposition and error propagation. To address these issues, we introduce Reasoning Tree Guided RAG (RT-RAG), a novel hierarchical framework for complex multi-hop QA. RT-RAG systematically decomposes multi-hop questions into explicit reasoning trees, minimizing inaccurate decomposition through structured entity analysis and consensus-based tree selection that clearly separates core queries, known entities, and unknown entities. Subsequently, a bottom-up traversal strategy employs iterative query rewriting and refinement to collect high-quality evidence, thereby mitigating error propagation. Comprehensive experiments show that RT-RAG substantially outperforms state-of-the-art methods by 7.0% F1 and 6.0% EM, demonstrating the effectiveness of RT-RAG in complex multi-hop QA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
