发表机构
University of Macau; Shenzhen Kaihong Digital Industry Development Co., Ltd.; University of New South Wales; Zhejiang University; Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（澳门大学; 深圳开鸿数字产业发展有限公司; 新南威尔士大学; 浙江大学; 中国科学院深圳先进技术研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究可解释多跳问答，提出HyCE-RAG框架，将实体等组织成超边构建超图，经置信度传播和证据组装选择连接证据路径，评分时考虑多种因素，实验证明其在多方面优于标准和基于图的RAG基线，为复杂问答检索后推理提供新方向。
AI 中文摘要
多跳问答要求系统从多个文档中检索证据并将分散的事实连接成连贯的推理过程。标准检索增强生成（RAG）主要依赖查询与文本块之间的语义相似性，常无法对实体、事实和证据单元之间的结构关系进行建模。基于图的RAG通过引入图结构知识改进了这一点，但成对边在表示涉及多个实体和上下文的高阶关联方面仍有局限。我们提出HyCE-RAG，一种用于可解释多跳问答的超图证据链检索增强生成框架。HyCE-RAG将实体、关系和上下文证据组织成超边，构建查询感知证据超图，并在实体-超边关联结构上进行置信度传播。然后使用置信度引导的证据组装在答案生成前选择、连接和排序证据路径。评分过程联合考虑语义相关性、实体连通性、证据覆盖范围、关系可靠性、提取置信度和传播置信度。通过为语言模型提供结构化证据链而非扁平的检索段落，HyCE-RAG支持更可靠和可解释的推理。在HotpotQA、2WikiMultihopQA、MuSiQue和两个GraphRAG-Bench子集上的实验表明，HyCE-RAG在答案准确性、上下文相关性和忠实性方面始终优于标准RAG和基于图的RAG基线。这些结果表明基于超图的证据组织是复杂问答中检索后推理的一个有前途的方向。
英文摘要
Multi-hop question answering requires systems to retrieve evidence from multiple documents and connect scattered facts into a coherent reasoning process. Standard retrieval-augmented generation (RAG) mainly relies on semantic similarity between a query and text chunks, and therefore often fails to model structural relations among entities, facts, and evidence units. Graph-based RAG improves this by introducing graph-structured knowledge, but pairwise edges are still limited in representing higher-order associations involving multiple entities and contexts. We propose HyCE-RAG, a Hypergraph Chain-of-Evidence Retrieval-Augmented Generation framework for explainable multi-hop question answering. HyCE-RAG organizes entities, relations, and contextual evidence into hyperedges, builds a query-aware evidence hypergraph, and performs confidence propagation over entity--hyperedge incidence structures. It then uses confidence-guided evidence assembly to select, connect, and rank evidence paths before answer generation. The scoring process jointly considers semantic relevance, entity connectivity, evidence coverage, relation reliability, extraction confidence, and propagated confidence. By providing the language model with structured evidence chains rather than flat retrieved passages, HyCE-RAG supports more faithful and interpretable reasoning. Experiments on HotpotQA, 2WikiMultihopQA, MuSiQue, and two GraphRAG-Bench subsets show that HyCE-RAG consistently outperforms standard RAG and graph-based RAG baselines in answer accuracy, context relevance, and faithfulness. These results suggest that hypergraph-based evidence organization is a promising direction for post-retrieval reasoning in complex question answering.
Comments15 pages, 3 figures, 4 tables
