PLForge: Enhancing Language Models for Natural Language to Procedural Extensions of SQL
Summary: Defines NL-to-PL/SQL to target procedural, multi-statement PL/SQL generation that Text-to-SQL models neglect. Introduces PLForge (3/7/15B) via PL/SQL-centric incremental pretraining, custom prompting and synthetic NL–PL/SQL data, improving execution- and exact-match vs. baselines. (summarized by gpt-5-mini on Feb 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Hang Zhang (Tsinghua University)
- 2. Chaokun Wang (Tsinghua University)
- 3. Hongwei Li (Tsinghua University)
- 4. Cheng Wu (Tsinghua University)
- 5. Songyao Wang (Tsinghua University)
- 6. Yabin Liu (Tsinghua University)
- 7. Gengyuan Shi (Tsinghua University)
- 8. Ziyang Liu (Tsinghua University)
BibTeX Citation
@inproceedings{zhang_sigmod26,
title = {{PLForge: Enhancing Language Models for Natural Language to Procedural Extensions of SQL}},
author = {Zhang, Hang and Wang, Chaokun and Li, Hongwei and Wu, Cheng and Wang, Songyao and Liu, Yabin and Shi, Gengyuan and Liu, Ziyang},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769813},
url = {https://dl.acm.org/doi/10.1145/3769813},
year = {2026}
}
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 12 of 12 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 | 9,047 | SQL-Factory: A Multi-Agent Framework for High-Quality and Large-Scale SQL Generation | 2026 | VLDB |
| 2 | 10,510 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |
| 3 | 2,852 | The Dawn of Natural Language to SQL: Are We Fully Ready? | 2024 | VLDB |
| 4 | 4,602 | Provenance for Natural Language Queries | 2017 | VLDB |
| 5 | 9,763 | NLProv: Natural Language Provenance | 2016 | VLDB |
| 6 | 865 | Natural language to SQL: Where are we today? | 2020 | VLDB |
| 7 | 9,870 | Natural Language to SQL: State of the Art and Open Problems | 2025 | VLDB |
| 8 | 2,602 | NL2SQL is a solved problem... Not! | 2024 | CIDR |
| 9 | 2,748 | Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning | 2023 | SIGMOD |
| 10 | 2,079 | DBPal: A Fully Pluggable NL2SQL Training Pipeline | 2020 | SIGMOD |