AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation

TL;DR

AtomicRAG introduces a novel atom-entity graph approach for retrieval-augmented generation, replacing text chunks with knowledge atoms to enhance flexibility, accuracy, and reasoning robustness in knowledge retrieval.

Contribution

It proposes the Atom-Entity Graph architecture that stores knowledge as self-contained atoms, improving retrieval flexibility and reasoning reliability over traditional triple-based methods.

Findings

Outperforms strong RAG baselines in retrieval accuracy

Enhances reasoning robustness on five public benchmarks

Uses personalized PageRank for reliable entity connections

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.