Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
Summary: Systematic benchmark of prompt-engineering components (question representation, example selection/organization) and token-efficiency for LLM-based Text-to-SQL. Proposes DAIL-SQL (86.6% execution on Spider) and evaluates open-source LLMs with supervised fine-tuning, revealing accuracy/efficiency/cost trade-offs. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Dawei Gao (Alibaba)
- 2. Haibin Wang (Alibaba)
- 3. Yichen Qian (Alibaba)
- 4. Yaliang Li (Alibaba)
- 5. Bolin Ding (Alibaba)
- 6. Xiuyu Sun (Alibaba)
- 7. Jingren Zhou (Alibaba)
BibTeX Citation
@article{gao_vldb24,
title = {{Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation}},
author = {Gao, Dawei and Wang, Haibin and Qian, Yichen and Li, Yaliang and Ding, Bolin and Sun, Xiuyu and Zhou, Jingren},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {5},
pages = {1132--1145},
doi = {10.14778/3641204.3641221},
url = {https://doi.org/10.14778/3641204.3641221},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 5 of 55 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,882 | CatDB: Data-catalog-guided, LLM-based Generation of Data-centric ML Pipelines | 2025 | VLDB | 5.093636e-05 |
| 10,909 | LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation | 2025 | VLDB | 5.093636e-05 |
| 10,940 | Evoschema: Towards Text-To-Sql Robustness Against Schema Evolution | 2025 | VLDB | 5.093636e-05 |
| 10,983 | CEDAR: A System for Cost-Efficient Data-Driven Claim Verification | 2025 | VLDB | 5.093636e-05 |
| 11,013 | Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models | 2025 | VLDB | 5.093636e-05 |
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2,048 | Duoquest: A Dual-Specification System for Expressive SQL Queries | 2020 | SIGMOD | 9.2560185e-05 |
| 2,521 | CodexDB: Synthesizing Code for Query Processing from Natural Language Instructions using GPT-3 Codex | 2022 | VLDB | 8.4729505e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 2,710 | OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment | 2025 | SIGMOD |
| 2 | 6,936 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 3 | 10,217 | DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework | 2026 | SIGMOD |
| 4 | 2,395 | OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale | 2025 | VLDB |
| 5 | 3,787 | Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL | 2024 | VLDB |
| 6 | 756 | CodeS: Towards Building Open-source Language Models for Text-to-SQL | 2024 | SIGMOD |
| 7 | 5,174 | An In-Depth Benchmarking of Text-to-SQL Systems | 2021 | SIGMOD |
| 8 | 2,852 | The Dawn of Natural Language to SQL: Are We Fully Ready? | 2024 | VLDB |
| 9 | 10,510 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |
| 10 | 10,556 | OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision | 2026 | VLDB |