SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL
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_ | 1866910988952928256 |
|---|---|
| author | Gong, Yue Lei, Chuan Qin, Xiao Vaidya, Kapil Narayanaswamy, Balakrishnan Kraska, Tim |
| author_facet | Gong, Yue Lei, Chuan Qin, Xiao Vaidya, Kapil Narayanaswamy, Balakrishnan Kraska, Tim |
| contents | Text-to-SQL systems translate natural language (NL) questions into SQL queries, enabling non-technical users to interact with structured data. While large language models (LLMs) have shown promising results on the text-to-SQL task, they often produce semantically incorrect yet syntactically valid queries, with limited insight into their reliability. We propose SQLens, an end-to-end framework for fine-grained detection and correction of semantic errors in LLM-generated SQL. SQLens integrates error signals from both the underlying database and the LLM to identify potential semantic errors within SQL clauses. It further leverages these signals to guide query correction. Empirical results on two public benchmarks show that SQLens outperforms the best LLM-based self-evaluation method by 25.78% in F1 for error detection, and improves execution accuracy of out-of-the-box text-to-SQL systems by up to 20%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_04494 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL Gong, Yue Lei, Chuan Qin, Xiao Vaidya, Kapil Narayanaswamy, Balakrishnan Kraska, Tim Computation and Language Text-to-SQL systems translate natural language (NL) questions into SQL queries, enabling non-technical users to interact with structured data. While large language models (LLMs) have shown promising results on the text-to-SQL task, they often produce semantically incorrect yet syntactically valid queries, with limited insight into their reliability. We propose SQLens, an end-to-end framework for fine-grained detection and correction of semantic errors in LLM-generated SQL. SQLens integrates error signals from both the underlying database and the LLM to identify potential semantic errors within SQL clauses. It further leverages these signals to guide query correction. Empirical results on two public benchmarks show that SQLens outperforms the best LLM-based self-evaluation method by 25.78% in F1 for error detection, and improves execution accuracy of out-of-the-box text-to-SQL systems by up to 20%. |
| title | SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.04494 |