AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908987657551872 |
|---|---|
| author | Hou, Yanning Yuan, Duanyang Zhou, Sihang Chen, Xiaoshu Liang, Ke Wang, Siwei Liu, Xinwang Huang, Jian |
| author_facet | Hou, Yanning Yuan, Duanyang Zhou, Sihang Chen, Xiaoshu Liang, Ke Wang, Siwei Liu, Xinwang Huang, Jian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_20844 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation Hou, Yanning Yuan, Duanyang Zhou, Sihang Chen, Xiaoshu Liang, Ke Wang, Siwei Liu, Xinwang Huang, Jian Information Retrieval Artificial Intelligence 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. |
| title | AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2604.20844 |