SchemaRAG: A Schema-aware Retrieval-Augmented Generation Framework for Text-to-SQL
Summary: Schema-aware RAG for Text-to-SQL: fine-tuned SchemaLinker distills CoT/GRPO to align NL with schema items, plus schema-conditioned example retrieval. Pareto-optimal candidate selection boosts robustness/validity, outperforming prior LLM Text-to-SQL baselines. (summarized by gpt-5-mini on Apr 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Di Wu (Southwest University)
- 2. Zetong Tang (Southwest University)
- 3. Yi He (College of William & Mary)
- 4. Xin Luo (Southwest University)
BibTeX Citation
@inproceedings{wu_sigmod26,
title = {{SchemaRAG: A Schema-aware Retrieval-Augmented Generation Framework for Text-to-SQL}},
author = {Wu, Di and Tang, Zetong and He, Yi and Luo, Xin},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3786696},
url = {https://dl.acm.org/doi/10.1145/3786696},
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 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 533 | CodeS: Towards Building Open-source Language Models for Text-to-SQL | 2024 | SIGMOD | 0.00016826571 |
| 1,356 | CatSQL: Towards Real World Natural Language to SQL Applications | 2023 | VLDB | 0.00010925509 |
| 4,331 | FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis | 2024 | SIGMOD | 6.6590534e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 4,924 | SNAILS: Schema Naming Assessments for Improved LLM-Based SQL Inference | 2025 | SIGMOD |
| 2 | 174 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 3 | 3,466 | In-depth Analysis of Graph-based RAG in a Unified Framework | 2025 | VLDB |
| 4 | 10,766 | A Comparative Evaluation of Schema Subsetting for LLM-based NL-to-SQL over Large-Schema Databases | 2026 | VLDB |
| 5 | 4,718 | Chat2Data: An Interactive Data Analysis System with RAG, Vector Databases and LLMs | 2024 | VLDB |
| 6 | 10,781 | QA-GraphRAG: Query-Adaptive Plug-and-Play Retrieval Integration for Graph-based Retrieval-Augmented Generation | 2026 | VLDB |
| 7 | 7,012 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 8 | 2,606 | Text2SQL is Not Enough: Unifying AI and Databases with TAG | 2025 | CIDR |
| 9 | 3,489 | Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL | 2024 | VLDB |
| 10 | 11,160 | RTS+: Reliable Text to SQL | 2025 | SIGMOD |