Graph-based retrieval-augmented generation (RAG) methods, typically built on knowledge graphs (KGs) with binary relational facts, have shown promise in multi-hop open-domain QA. However, their rigid retrieval schemes and dense similarity search often introduce irrelevant context, increase computational overhead, and limit relational expressiveness. In contrast, n-ary hypergraphs encode higher-order relational facts that capture richer inter-entity dependencies and enable shallower, more efficient reasoning paths. To address this limitation, we propose HyperRAG, a RAG framework tailored for n-ary hypergraphs with two complementary retrieval variants: (i) HyperRetriever learns structural-semantic reasoning over n-ary facts to construct query-conditioned relational chains. It enables accurate factual tracking, adaptive high-order traversal, and interpretable multi-hop reasoning under context constraints. (ii) HyperMemory leverages the LLM's parametric memory to guide beam search, dynamically scoring n-ary facts and entities for query-aware path expansion. Extensive evaluations on WikiTopics (11 closed-domain datasets) and three open-domain QA benchmarks (HotpotQA, MuSiQue, and 2WikiMultiHopQA) validate HyperRAG's effectiveness. HyperRetriever achieves the highest answer accuracy overall, with average gains of 2.95% in MRR and 1.23% in Hits@10 over the strongest baseline. Qualitative analysis further shows that HyperRetriever bridges reasoning gaps through adaptive and interpretable n-ary chain construction, benefiting both open and closed-domain QA.

翻译：基于图的检索增强生成（RAG）方法通常构建在包含二元关系事实的知识图谱（KG）之上，已在多跳开放域问答中展现出潜力。然而，其僵化的检索方案和密集相似性搜索常常引入无关上下文、增加计算开销并限制关系表达能力。相比之下，多元超图编码了高阶关系事实，能够捕捉更丰富的实体间依赖关系，并支持更浅层、更高效的推理路径。为应对这一局限，我们提出HyperRAG——一个专为多元超图设计的RAG框架，包含两种互补的检索变体：（i）HyperRetriever学习对多元事实进行结构语义推理，以构建查询条件化的关系链。它能在上下文约束下实现精确的事实追踪、自适应的高阶遍历和可解释的多跳推理。（ii）HyperMemory利用大语言模型（LLM）的参数化记忆引导束搜索，动态评估多元事实与实体以进行查询感知的路径扩展。在WikiTopics（11个封闭域数据集）和三个开放域问答基准（HotpotQA、MuSiQue和2WikiMultiHopQA）上的广泛评估验证了HyperRAG的有效性。HyperRetriever实现了最高的整体答案准确率，在MRR和Hits@10指标上分别较最强基线平均提升2.95%和1.23%。定性分析进一步表明，HyperRetriever通过自适应且可解释的多元链构建弥合了推理鸿沟，对开放域和封闭域问答均有助益。