知识并非静态：面向语言模型的顺序感知超图RAG
Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models
AI总结：
本文提出顺序感知超图RAG（OKH-RAG），通过将顺序作为结构属性，改进传统RAG方法，提升对顺序敏感任务的推理能力。
摘要：
检索增强生成（RAG）通过将输出与检索到的知识联系起来来增强大型语言模型。然而，现有RAG方法，包括基于图和超图的方法，将检索到的证据视为无序集合，隐含假设了排列不变性。这一假设与许多现实世界的推理任务不一致，其中结果不仅取决于发生的相互作用，还取决于它们发生的顺序。我们提出顺序感知知识超图RAG（OKH-RAG），将顺序作为第一类结构属性。OKH-RAG将知识表示为超图中更高阶的相互作用，超图附加了优先级结构，并将检索重新表述为超边上的序列推断。而不是选择独立的事实，它恢复了反映潜在推理过程的连贯相互作用轨迹。一个学习的转换模型从数据中直接推断优先级，而无需显式的时序监督。我们在对顺序敏感的问题回答和解释任务中评估OKH-RAG，包括热带气旋和港口操作场景。OKH-RAG在顺序敏感的问题回答和解释任务中一致优于排列不变的基线，并且消融实验显示这些收益源于对相互作用顺序的建模。这些结果突显了基于集合的检索的关键限制：有效的推理不仅需要检索相关证据，还需要将其组织成结构化的序列。
英文摘要：
Retrieval-augmented generation (RAG) enhances large language models by grounding outputs in retrieved knowledge. However, existing RAG methods including graph- and hypergraph-based approaches treat retrieved evidence as an unordered set, implicitly assuming permutation invariance. This assumption is misaligned with many real-world reasoning tasks, where outcomes depend not only on which interactions occur, but also on the order in which they unfold. We propose Order-Aware Knowledge Hypergraph RAG (OKH-RAG), which treats order as a first-class structural property. OKH-RAG represents knowledge as higher-order interactions within a hypergraph augmented with precedence structure, and reformulates retrieval as sequence inference over hyperedges. Instead of selecting independent facts, it recovers coherent interaction trajectories that reflect underlying reasoning processes. A learned transition model infers precedence directly from data without requiring explicit temporal supervision. We evaluate OKH-RAG on order-sensitive question answering and explanation tasks, including tropical cyclone and port operation scenarios. OKH-RAG consistently outperforms permutation-invariant baselines, and ablations show that these gains arise specifically from modeling interaction order. These results highlight a key limitation of set-based retrieval: effective reasoning requires not only retrieving relevant evidence, but organizing it into structured sequences.
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。
