Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding
Summary: Builds reusable NL–SQL templates from labeled workloads and uses a fine-tuned NLI selector to match/reject incoming queries. Enforces chosen template via partitioned grammar-constrained decoding for valid, efficient SQL, yielding up to +36% exec accuracy over ICL and 2.2× lower latency on matched queries. (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. Smit Jivani (Indian Institute of Technology Mumbai)
- 2. Sarvam Maheshwari (Indian Institute of Technology Mumbai)
- 3. Sunita Sarawagi (Indian Institute of Technology Mumbai)
BibTeX Citation
@inproceedings{jivani_sigmod26,
title = {{Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding}},
author = {Jivani, Smit and Maheshwari, Sarvam and Sarawagi, Sunita},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769822},
url = {https://dl.acm.org/doi/10.1145/3769822},
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 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 174 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB | 0.00026790979 |
| 180 | Constructing an Interactive Natural Language Interface for Relational Databases | 2015 | VLDB | 0.0002654471 |
| 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 |
| 2,025 | OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment | 2025 | SIGMOD | 9.163622e-05 |
| 3,489 | Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL | 2024 | VLDB | 7.2627807e-05 |
| 5,227 | Natural Language Data Management and Interfaces: Recent Development and Open Challenges | 2017 | SIGMOD | 6.2199469e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 174 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 2 | 10,893 | Developing and Benchmarking Verification Algorithms to Improve Text-to-SQL Generation | 2026 | VLDB |
| 3 | 2,467 | Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning | 2023 | SIGMOD |
| 4 | 3,489 | Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL | 2024 | VLDB |
| 5 | 10,497 | Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards | 2026 | SIGMOD |
| 6 | 3,743 | Logical and Physical Optimizations for SQL Query Execution over Large Language Models | 2025 | SIGMOD |
| 7 | 7,952 | The Power of Constraints in Natural Language to SQL Translation | 2025 | VLDB |
| 8 | 11,160 | RTS+: Reliable Text to SQL | 2025 | SIGMOD |
| 9 | 7,012 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 10 | 10,832 | ReSequel: Robust LLM-assisted Query Rewriting and Optimization using Templatization and Sampling | 2026 | VLDB |