Safety
AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation
arXiv:2604.20844v1 Announce Type: cross Abstract: Recent GraphRAG methods integrate graph structures into text indexing and retrieval, using knowledge graph triples to connect text chunks, thereby imp
arXiv:2604.20844v1 Announce Type: cross Abstract: Recent GraphRAG methods integrate graph structures into text indexing and retrieval, using knowledge graph triples to connect text chunks, thereby improving retrieval coverage and precision. However, we observe that treating text chunks as the basic unit of knowledge representation rigidly groups multiple atomic facts together, limiting the flexibility and adaptability needed to support diverse retrieval scenarios. Additionally, triple-based entity linking is sensitive to relation-extraction errors, which can lead to missing or incorrect reasoning paths and ultimately hurt retrieval accuracy. To address these issues, we propose the Atom-Entity Graph, a more precise and reliable architecture for knowledge representation and indexing. In our approach, knowledge is stored as knowledge atoms, namely individual, self-contained units of factual information, rather than coarse-grained text chunks. This allows knowledge elements to be flexibly reassembled without mutual interference, thereby enabling seamless alignment with diverse query perspectives. Edges between entities simply indicate whether a relationship exists. By combining personalized PageRank with relevance-based filtering, we maintain accurate entity connections and improve the reliability of reasoning. Theoretical analysis and experiments on five public benchmarks show that the proposed AtomicRAG algorithm outperforms strong RAG baselines in retrieval accuracy and reasoning robustness. Code: https://github.com/7HHHHH/AtomicRAG.
Related
- GRAIL:Learning to Interact with Large Knowledge Graphs for Retrieval Augmented Reasoning
- ERA: Evidence-based Reliability Alignment for Honest Retrieval-Augmented Generation
- Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation
- HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG
- AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction
Source: arXiv cs.AI | 2026-04-24