NeutronRAG: Towards Understanding the Effectiveness of RAG from a Data Retrieval Perspective
Summary: NeutronRAG is a data-retrieval–driven demonstration to understand RAG effectiveness across retrieval paradigms (VectorRAG, GraphRAG, HybridRAG). It offers hybrid retrieval, systematic analysis, visual feedback, and parameter-adjustment guidance for data-driven comparison of retrieval methods and settings. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Peizheng Li (Northeastern University)
- 2. Chaoyi Chen (Northeastern University)
- 3. Hao Yuan (Northeastern University)
- 4. Zhenbo Fu (Northeastern University)
- 5. Hang Shen (Northeastern University)
- 6. Xinbo Yang (Northeastern University)
- 7. Qiange Wang (National University of Singapore)
- 8. Xin Ai (Northeastern University)
- 9. Yanfeng Zhang (Northeastern University)
- 10. Ge Yu (Northeastern University)
- 11. Yingyou Wen (Neusoft Corporation)
BibTeX Citation
@inproceedings{li_sigmod25,
title = {{NeutronRAG: Towards Understanding the Effectiveness of RAG from a Data Retrieval Perspective}},
author = {Li, Peizheng and Chen, Chaoyi and Yuan, Hao and Fu, Zhenbo and Shen, Hang and Yang, Xinbo and Wang, Qiange and Ai, Xin and Zhang, Yanfeng and Yu, Ge and Wen, Yingyou},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3722212.3725119},
url = {https://dl.acm.org/doi/10.1145/3722212.3725119},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,357 | DepCache: A KV Cache Management Framework for GraphRAG with Dependency Attention | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 0 of 0 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next