Developing and Benchmarking Verification Algorithms to Improve Text-to-SQL Generation
Summary: Formalizes Text-to-SQL verification without ground-truth labels, comparing round-trip critique with synthetic execution consistency. Flags 64% of generator errors, exposes widespread benchmark-label flaws, and enables selective generation that abstains on low-confidence queries. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Tarfah Alrashed (Google)
- 2. Madhup Sukoon (Google)
- 3. David R. Karger (Google)
- 4. Natasha Noy (Google)
BibTeX Citation
@article{alrashed_vldb26,
title = {{Developing and Benchmarking Verification Algorithms to Improve Text-to-SQL Generation}},
author = {Alrashed, Tarfah and Sukoon, Madhup and Karger, David R. and Noy, Natasha},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {11},
pages = {3732--3744},
doi = {10.14778/3836663.3836721},
url = {https://doi.org/10.14778/3836663.3836721},
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 |
|---|---|---|---|---|
| 163 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB | 0.00027456647 |
| 4,851 | Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL | 2025 | VLDB | 6.3681831e-05 |
| 7,658 | Test Data Generation for Complex SQL Queries | 2026 | SIGMOD | 5.4565877e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,837 | A Comparative Evaluation of Schema Subsetting for LLM-based NL-to-SQL over Large-Schema Databases | 2026 | VLDB |
| 2 | 10,851 | SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL | 2026 | VLDB |
| 3 | 10,382 | Automated Database Testing via LLM-Synthesized SQL Features | 2027 | SIGMOD |
| 4 | 10,383 | Benchmarking Text-to-SQL under Role-Based Access Control | 2027 | SIGMOD |
| 5 | 163 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 6 | 9,754 | Leveraging Query Optimizers to Verify the Soundness of LLM-based Query Rewrites for Real-World Workloads, and More! | 2026 | CIDR |
| 7 | 10,511 | DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework | 2026 | SIGMOD |
| 8 | 10,766 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |
| 9 | 4,917 | Automated Validating and Fixing of Text-to-SQL Translation with Execution Consistency | 2025 | SIGMOD |
| 10 | 6,528 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |