双超图索引：弥合知识孤岛以增强检索增强生成中的多跳推理
Dual-Hypergraph Indexing: Bridging Knowledge Islands for Multi-Hop Reasoning in Retrieval-Augmented Generation
AI总结：
提出双超图索引（DHI），通过双路径聚合耦合事实超图与洞察超图，打破知识孤岛，在多跳RAG中实现最先进性能，显著提升逻辑连贯性与复杂推理准确率。
AI中文摘要：
虽然基于超图的检索增强生成（RAG）能够有效捕获高阶多实体关联，但现有范式将提取的超边视为孤立的事实断言。这种结构碎片化导致了僵化的“知识孤岛”，成为多跳因果推理、时间追踪和叙事综合的瓶颈。为系统性地应对这些挑战，我们提出了双超图索引（DHI），一种将离散事实提升为结构化分析见解的分层表示框架。DHI通过双路径聚合算法，将基础实体-关系事实超图（$H_K$）与高层深度洞察超图（$H_D$）耦合。具体而言，DHI采用：（1）基于重要性驱动的枢纽聚合，通过5指标拓扑分析和自适应阈值处理来捕获空间语义聚类；（2）基于时间块链的渐进聚合，通过滑动窗口贪婪探索来追踪时间演化。在五个基准测试中，DHI达到了最先进的性能，在多学科Mix基准上将逻辑连贯性提升了+1.53，并在复杂医学病理推理任务中取得了85.78%的得分。DHI为下一代多跳RAG提供了稳健的架构。
英文摘要：
While hypergraph-based Retrieval-Augmented Generation (RAG) effectively captures higher-order multi-entity correlations, existing paradigms treat extracted hyperedges as isolated factual assertions. This structural fragmentation engenders rigid "knowledge islands" that bottleneck multi-hop causal inference, temporal tracking, and narrative synthesis. To systematically address these challenges, we introduce Dual-Hypergraph Indexing (DHI), a hierarchical representation framework that elevates discrete facts into structured analytical insights. DHI couples a foundational entity-relation factual hypergraph ($H_K$) with an elevated deep-insight hypergraph ($H_D$) via a dual-pathway aggregation algorithm. Specifically, DHI employs: (1) importance-driven hub aggregation via 5-metric topological profiling and adaptive thresholding to capture spatial semantic clusters; and (2) temporal chunk-chain progressive aggregation via sliding-window greedy exploration to track chronological evolutions. Across five benchmarks, DHI achieves state-of-the-art performance, boosting logical coherence by +1.53 on the multidisciplinary Mix benchmark and scoring 85.78\% on complex medical pathology reasoning tasks. DHI provides a robust architecture for next-generation multi-hop RAG.
