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

Arabic

وفي الوقت نفسه، فإن نموذج EMG (RAG) يمتد من خلال نموذج EMG (RAG) إلى نموذج EMG (RAG) يمتد من خلال نموذج EMG (RAG) إلى نموذج EMG (RAG) يمتد من خلال نموذج EMG (RAG) إلى نموذج EMG (RAG) يمتد من خلال نموذج EMG (RAG) إلى نموذج EMG (RAG) يمتد من خلال نموذج EMG (RAG) إلى نموذج EMG (RAG) إلى نموذج EMG (RAG) يمتد من خلال نموذج EMG (RAG) إلى نموذج EMG (RAG) إلى نموذج EMG (RAG) إلى نموذج

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