Newest papers

Graph Topology Meets Energy-Driven Pathfinding: Preserving Contextual Consistency in Retrieval-Augmented Generation

Yufeng Li, Zaijing Li, F. Zhang, Zongzong Wu, Ming Zhao, Fengxiao Tang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29933 · cited by 0 works (OpenAlex) · open-access PDF

Korean

그러나, 그들의 성능은 점점 더 지식 구조화 및 논리 프로세스에 의해 배틀링됩니다. (i) 심각한 시멘틱 손실: 분리 된 상징으로 지속적인 텍스트를 분리하는 것은 컨텍스트 뉘앙스와 이야기를 일관성을 제거합니다. (ii) 분리 된 그래프 구조가 LLM의 지속적인 텍스트와 충돌하는 동안. (i) 심각한 시멘틱 손실: 분리 된 상징으로 지속적인 텍스트를 분리하는 것은 이러한 한계를 제거하기 위해 ThreadRAG, 컨텍스트 보존 지식 구조화 및 모탈리티 원형 증거 논리에 대한 시멘틱 토픽 기반 RAG 프레임 워크를 제안합니다. ThRAG는 강력한 QSTM을 도입합니다. 그것은 텍스트 토픽

Machine translation (Meta M2M100); the English original follows.

Abstract

Retrieval-augmented generation (RAG) frequently integrates knowledge graphs (KGs) for complex multi-hop question answering. However, their performance is increasingly bottlenecked by the knowledge structuring and reasoning processes. (i) Severe semantic loss: Distilling continuous texts into discrete symbols strips away contextual nuances and narrative coherence. (ii) Pronounced modality mismatch: Fragmented graph structures clash with the continuous texts LLMs are pre-trained on, while rewriting them into natural language introduces generative noise and omits information. To address these limitations, we propose ThreadRAG, a semantic-topology-based RAG framework for context-preserving knowledge structuring and modality-native evidence reasoning. ThreadRAG introduces a Semantic Topology Mapper (STM), which organizes retrieved documents into context-intact Semantic Nodes and constructs a Semantic Topology Graph (STG) through narrative, semantic, and lexical edges. It further incorporates Energy-Driven Pathfinding (EDP), which identifies query-relevant subgraphs via energy diffusion and deterministically linearizes them into coherent textual evidence paths. Experiments on three multi-hop QA benchmarks demonstrate that ThreadRAG consistently outperforms strong baselines. Notably, it achieves a 14.4% EM improvement over text-centric methods on HotpotQA and surpasses the best baseline by 5.8% EM on 2WikiMultihop, while reducing token cost to 23.3% of the strongest baseline.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Theoretical computer science, Structuring, Graph, Security token, Consistency (knowledge bases)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange