In-depth Analysis of Graph-based RAG in a Unified Framework
Summary: Unifies graph-based RAG approaches into a single framework and systematically benchmarks representative methods under identical settings across specific and abstract QA tasks. Finds hybrid variants that outperform prior SOTA on subsets and extracts empirical insights and future directions for graph-augmented LLMs. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Yingli Zhou (Chinese University of Hong Kong)
- 2. Yaodong Su (Chinese University of Hong Kong)
- 3. Youran Sun (Chinese University of Hong Kong)
- 4. Shu Wang (Chinese University of Hong Kong)
- 5. Taotao Wang (Chinese University of Hong Kong)
- 6. Runyuan He (Chinese University of Hong Kong)
- 7. Yongwei Zhang (Huawei Cloud Computing Technologies Co., Ltd.)
- 8. Sicong Liang (Huawei Cloud Computing Technologies Co., Ltd.)
- 9. Xilin Liu (Huawei Cloud Computing Technologies Co., Ltd.)
- 10. Yuchi Ma (Huawei Cloud Computing Technologies Co., Ltd.)
- 11. Yixiang Fang (Chinese University of Hong Kong)
BibTeX Citation
@article{zhou_vldb25,
title = {{In-depth Analysis of Graph-based RAG in a Unified Framework}},
author = {Zhou, Yingli and Su, Yaodong and Sun, Youran and Wang, Shu and Wang, Taotao and He, Runyuan and Zhang, Yongwei and Liang, Sicong and Liu, Xilin and Ma, Yuchi and Fang, Yixiang},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {13},
pages = {5623--5637},
doi = {10.14778/3773731.3773738},
url = {https://doi.org/10.14778/3773731.3773738},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 5 of 5 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,201 | Balancing Global and Local: Representative Sampling for Large-Scale Vector Data | 2026 | SIGMOD | 5.093636e-05 |
| 10,204 | Beyond Maximum Common Subgraph: A Framework Maximizing Shared Computation for Multi-Query Subgraph Matching | 2026 | SIGMOD | 5.093636e-05 |
| 10,253 | HAMMER: An Automatic RAG Tuning System via Hierarchical Memory-Guided Monte Carlo Tree Search | 2026 | SIGMOD | 5.093636e-05 |
| 10,290 | Skyline Retrieval meets Set-Cover Chunk Merging: A Cost-Effective RAG-Sketch for Long-Context LLM QA | 2026 | SIGMOD | 5.093636e-05 |
| 10,627 | Revisiting Task-Oriented Dataset Search in the Era of Large Language Models: Challenges, Benchmark, and Solution | 2026 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 15 of 15 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next