The Power of Constraints in Natural Language to SQL Translation
Summary: REDSQL: plug-and-play refiner that uses constraint-driven extraction of relation summaries and data profiles over the entire DB to detect and fix semantic SQL errors beyond LLM context limits. Yields large NL2SQL gains (e.g., +8.8% CODES, +11.1% PURPLE on BIRD). (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Tonghui Ren (Fudan University; Tencent Cloud)
- 2. Chen Ke (Fudan University)
- 3. Yuankai Fan (China Telecom; Fudan University; TeleAI)
- 4. Yinan Jing (Fudan University)
- 5. Zhenying He (Fudan University)
- 6. Kai Zhang (Fudan University)
- 7. X. Sean Wang (Fudan University)
BibTeX Citation
@article{ren_vldb25,
title = {{The Power of Constraints in Natural Language to SQL Translation}},
author = {Ren, Tonghui and Ke, Chen and Fan, Yuankai and Jing, Yinan and He, Zhenying and Zhang, Kai and Wang, X. Sean},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {7},
pages = {2097--2111},
doi = {10.14778/3734839.3734847},
url = {https://doi.org/10.14778/3734839.3734847},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,556 | OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision | 2026 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 18 of 18 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
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 2,553 | LLM-R^2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency | 2025 | VLDB |
| 2 | 10,732 | RTS+: Reliable Text to SQL | 2025 | SIGMOD |
| 3 | 865 | Natural language to SQL: Where are we today? | 2020 | VLDB |
| 4 | 2,852 | The Dawn of Natural Language to SQL: Are We Fully Ready? | 2024 | VLDB |
| 5 | 1,444 | CatSQL: Towards Real World Natural Language to SQL Applications | 2023 | VLDB |
| 6 | 10,510 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |
| 7 | 2,602 | NL2SQL is a solved problem... Not! | 2024 | CIDR |
| 8 | 6,936 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 9 | 9,870 | Natural Language to SQL: State of the Art and Open Problems | 2025 | VLDB |
| 10 | 3,787 | Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL | 2024 | VLDB |