AI 中文总结
提出HyperReCo框架，利用超图神经网络学习查询依赖交互以检索互补证据，并通过梯度引导超路径解码显式连接证据，提升LLM多跳推理性能，在三个多跳QA数据集上取得最优检索效果。
AI 中文摘要
大型语言模型（LLMs）已展现出强大的能力，其中检索增强生成（RAG）通过检索分布在多个文档中的证据来支持复杂的多跳推理。基于图的方法利用证据之间的连接，而基于超图的检索进一步保留了文档内实体间的高阶关联，并通过共享实体连接不同文档。然而，现有的超图检索器往往依赖于预定义的结构扩展或扩散，这可能会遗漏识别相关证据所需的查询依赖交互。此外，它们还使检索到的证据之间的连接保持隐式，要求LLMs在推理前自行重建这些连接。因此，我们提出了HyperReCo，一个利用超图神经网络（HyperGNN）检索并连接证据的框架。我们将每个文档表示为其提取实体上的一个超边，共享实体则连接各超边。通过对文档和实体的联合监督进行超图消息传递，HyperGNN能够学习查询依赖的交互以检索互补证据。我们进一步引入了梯度引导超路径解码（GGHD），它利用梯度归因来解释学习到的交互，并将其转化为显式的超路径，帮助LLMs组合互补事实进行多跳推理。在六个基准上的实验表明，HyperReCo在所有三个多跳问答数据集上均取得了优于对比方法的最佳检索性能，同时在下游问答任务上也表现出强劲性能。案例研究和进一步分析证明了所解码超路径在连接检索证据方面的实用性。
英文摘要
Large language models (LLMs) have shown strong capabilities, with retrieval-augmented generation (RAG) supporting complex multi-hop reasoning by retrieving evidence distributed across documents. Graph-based approaches exploit connections among evidence, and hypergraph-based retrieval further preserves higher-order entity associations within documents and connects documents through shared entities. However, existing hypergraph retrievers often rely on predefined structural expansion or diffusion, which may miss query-dependent interactions needed to identify relevant evidence. They also leave connections among retrieved evidence implicit, requiring LLMs to reconstruct these connections before reasoning. Therefore, we propose HyperReCo, a framework for retrieving and connecting evidence with a hypergraph neural network (HyperGNN). We represent each document as a hyperedge over its extracted entities, with shared entities connecting the hyperedges. Through hypergraph message passing with joint supervision over documents and entities, the HyperGNN learns query-dependent interactions to retrieve complementary evidence. We further introduce Gradient-Guided Hyper-Path Decoding (GGHD), which uses gradient attribution to interpret the learned interactions and translate them into explicit hyper-paths that help LLMs combine complementary facts for multi-hop reasoning. Experiments on six benchmarks show that HyperReCo achieves the best retrieval performance among the compared methods on all three multi-hop QA datasets, together with strong downstream QA performance. Case studies and further analyses demonstrate the utility of decoded hyper-paths for connecting retrieved evidence.
Comments22 pages, 6 figures
