DBScholar

Back to papers

LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration

Summary: LEGO-GraphRAG decomposes GraphRAG into fine-grained, composable modules, classifying existing techniques and enabling systematic instance construction. Large-scale experiments expose trade-offs among reasoning quality, latency, and token/GPU cost. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID
h6a662631b7f17820
Venue
VLDB
Year
2025
Pagerank
6.8550917e-05
Overall Rank
4,012 | 73.03%
DOI
10.14778/3748191.3748194

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{cao_vldb25,
        title = {{LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration}},
        author = {Cao, Yukun and Gao, Zengyi and Li, Zhiyang and Xie, Xike and Zhou, S. Kevin and Xu, Jianliang},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {10},
        pages = {3269--3283},
        doi = {10.14778/3748191.3748194},
        url = {https://doi.org/10.14778/3748191.3748194},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 5 of 5 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 9 of 9 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers