CodeS: Towards Building Open-source Language Models for Text-to-SQL
Summary: Open-source text-to-SQL LMs (1B–15B) that beat closed LLM SOTA, with SQL-centric incremental pretraining. Key tricks: schema-linking/domain-adaptation via prompt design + bidirectional augmentation; strong gains on Spider, BIRD, robustness, and real-world datasets. (summarized by gpt-5.4-mini on May 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Haoyang Li (Renmin University of China)
- 2. Jing Zhang (Renmin University of China)
- 3. Hanbing Liu (Renmin University of China)
- 4. Ju Fan (Renmin University of China)
- 5. Xiaokang Zhang (Renmin University of China)
- 6. Jun Zhu (Beijing AI-Finance Technologies Co. Ltd.)
- 7. Renjie Wei (Beijing AI-Finance Technologies Co. Ltd.)
- 8. Hongyan Pan (Beijing AI-Finance Technologies Co. Ltd.)
- 9. Cuiping Li (Renmin University of China)
- 10. Hong Chen (Renmin University of China)
BibTeX Citation
@inproceedings{li_sigmod24,
title = {{CodeS: Towards Building Open-source Language Models for Text-to-SQL}},
author = {Li, Haoyang and Zhang, Jing and Liu, Hanbing and Fan, Ju and Zhang, Xiaokang and Zhu, Jun and Wei, Renjie and Pan, Hongyan and Li, Cuiping and Chen, Hong},
series = {{SIGMOD} '24},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3654930},
url = {https://dl.acm.org/doi/10.1145/3654930},
year = {2024}
}
Incoming Citations (Sorted by Pagerank)
Showing 36 of 36 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 279 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB | 0.00022468369 |
| 1,444 | CatSQL: Towards Real World Natural Language to SQL Applications | 2023 | VLDB | 0.00010769944 |
| 2,039 | ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems | 2024 | VLDB | 9.2721259e-05 |
| 2,748 | Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning | 2023 | SIGMOD | 8.1707811e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,305 | The Power of Constraints in Natural Language to SQL Translation | 2025 | VLDB |
| 2 | 10,510 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |
| 3 | 6,936 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 4 | 10,732 | RTS+: Reliable Text to SQL | 2025 | SIGMOD |
| 5 | 2,748 | Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning | 2023 | SIGMOD |
| 6 | 2,710 | OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment | 2025 | SIGMOD |
| 7 | 2,395 | OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale | 2025 | VLDB |
| 8 | 2,521 | CodexDB: Synthesizing Code for Query Processing from Natural Language Instructions using GPT-3 Codex | 2022 | VLDB |
| 9 | 279 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 10 | 10,556 | OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision | 2026 | VLDB |