LLM-R^2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency
Summary: LLM-R² augments rule-based SQL rewriting with an LLM that recommends effective rewrite rules, guided by curriculum-trained contrastive query representations and demonstrations. It improves execution efficiency while reducing reliance on inaccurate cost estimators and remains robust across datasets. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Zhaodonghui Li (Alibaba; Nanyang Technological University)
- 2. Haitao Yuan (Nanyang Technological University)
- 3. Gao Cong (Nanyang Technological University)
- 4. Huiming Wang (Singapore Institute of Technology)
- 5. Lidong Bing (Alibaba)
BibTeX Citation
@article{li_vldb25,
title = {{LLM-R\^{}2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency}},
author = {Li, Zhaodonghui and Yuan, Haitao and Cong, Gao and Wang, Huiming and Bing, Lidong},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {1},
pages = {53--65},
doi = {10.14778/3696435.3696440},
url = {https://doi.org/10.14778/3696435.3696440},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 24 of 24 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 11 of 11 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next