SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912942414364672 |
|---|---|
| author | Klopfenstein, Rocky He, Yang Tremante, Andrew Wang, Yuepeng Narodytska, Nina Wu, Haoze |
| author_facet | Klopfenstein, Rocky He, Yang Tremante, Andrew Wang, Yuepeng Narodytska, Nina Wu, Haoze |
| contents | Community-driven Text-to-SQL evaluation platforms play a pivotal role in tracking the state of the art of Text-to-SQL performance. The reliability of the evaluation process is critical for driving progress in the field. Current evaluation methods are largely test-based, which involves comparing the execution results of a generated SQL query and a human-labeled ground-truth on a static test database. Such an evaluation is optimistic, as two queries can coincidentally produce the same output on the test database while actually being different. In this work, we propose a new alternative evaluation pipeline, called SpotIt, where a formal bounded equivalence verification engine actively searches for a database that differentiates the generated and ground-truth SQL queries. We develop techniques to extend existing verifiers to support a richer SQL subset relevant to Text-to-SQL. A performance evaluation of ten Text-to-SQL methods on the high-profile BIRD dataset suggests that test-based methods can often overlook differences between the generated query and the ground-truth. Further analysis of the verification results reveals a more complex picture of the current Text-to-SQL evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_26840 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification Klopfenstein, Rocky He, Yang Tremante, Andrew Wang, Yuepeng Narodytska, Nina Wu, Haoze Databases Artificial Intelligence Formal Languages and Automata Theory Logic in Computer Science Community-driven Text-to-SQL evaluation platforms play a pivotal role in tracking the state of the art of Text-to-SQL performance. The reliability of the evaluation process is critical for driving progress in the field. Current evaluation methods are largely test-based, which involves comparing the execution results of a generated SQL query and a human-labeled ground-truth on a static test database. Such an evaluation is optimistic, as two queries can coincidentally produce the same output on the test database while actually being different. In this work, we propose a new alternative evaluation pipeline, called SpotIt, where a formal bounded equivalence verification engine actively searches for a database that differentiates the generated and ground-truth SQL queries. We develop techniques to extend existing verifiers to support a richer SQL subset relevant to Text-to-SQL. A performance evaluation of ten Text-to-SQL methods on the high-profile BIRD dataset suggests that test-based methods can often overlook differences between the generated query and the ground-truth. Further analysis of the verification results reveals a more complex picture of the current Text-to-SQL evaluation. |
| title | SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification |
| topic | Databases Artificial Intelligence Formal Languages and Automata Theory Logic in Computer Science |
| url | https://arxiv.org/abs/2510.26840 |