Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.09295 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915998409424896 |
|---|---|
| author | Tan, Zhao Liu, Xiping Shu, Qing Wan, Qizhi Liu, Dexi Wan, Changxuan |
| author_facet | Tan, Zhao Liu, Xiping Shu, Qing Wan, Qizhi Liu, Dexi Wan, Changxuan |
| contents | Text-to-SQL translates natural language questions into executable SQL queries, enabling intuitive database access for non-experts. While large language models achieve strong performance on Text-to-SQL with prompting, they still struggle with complex queries that involve deeply nested logic or multiple clauses. A widely used approach employs SQL skeletons--intermediate representations of query logic--to streamline generation, but existing methods are limited by their reliance on a single structural hypothesis and lack of progressive reasoning. To overcome these limitations, we propose LEAF-SQL, a novel framework that reframes skeleton prediction as a coarse-to-fine tree search process. LEAF-SQL enables systematic exploration of diverse structural hypotheses with adaptive refinement. Several key techniques are employed in LEAF-SQL: (1) a three-level skeleton hierarchy to guide the search, (2) a Skeleton Formulation Agent to generate diverse candidates, and (3) a Skeleton Evaluation Agent to efficiently prune the search space. This integrated design yields skeleton candidates that are both structurally diverse and granularity-adaptive, providing a stronger foundation for the SQL generation. Extensive experiments show that LEAF-SQL consistently improves the performance of various LLM backbones. On the official hidden test set of the challenging BIRD benchmark, our method achieves 71.6 execution accuracy, which outperforms leading search-based and skeleton-based methods, affirming its effectiveness for complex queries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_09295 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LEAF-SQL: Level-wise Exploration with Adaptive Fine-graining for Text-to-SQL Skeleton Prediction Tan, Zhao Liu, Xiping Shu, Qing Wan, Qizhi Liu, Dexi Wan, Changxuan Computation and Language Text-to-SQL translates natural language questions into executable SQL queries, enabling intuitive database access for non-experts. While large language models achieve strong performance on Text-to-SQL with prompting, they still struggle with complex queries that involve deeply nested logic or multiple clauses. A widely used approach employs SQL skeletons--intermediate representations of query logic--to streamline generation, but existing methods are limited by their reliance on a single structural hypothesis and lack of progressive reasoning. To overcome these limitations, we propose LEAF-SQL, a novel framework that reframes skeleton prediction as a coarse-to-fine tree search process. LEAF-SQL enables systematic exploration of diverse structural hypotheses with adaptive refinement. Several key techniques are employed in LEAF-SQL: (1) a three-level skeleton hierarchy to guide the search, (2) a Skeleton Formulation Agent to generate diverse candidates, and (3) a Skeleton Evaluation Agent to efficiently prune the search space. This integrated design yields skeleton candidates that are both structurally diverse and granularity-adaptive, providing a stronger foundation for the SQL generation. Extensive experiments show that LEAF-SQL consistently improves the performance of various LLM backbones. On the official hidden test set of the challenging BIRD benchmark, our method achieves 71.6 execution accuracy, which outperforms leading search-based and skeleton-based methods, affirming its effectiveness for complex queries. |
| title | LEAF-SQL: Level-wise Exploration with Adaptive Fine-graining for Text-to-SQL Skeleton Prediction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.09295 |