Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.00391 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915315774914560 |
|---|---|
| author | Qu, Ge Li, Jinyang Qin, Bowen Li, Xiaolong Huo, Nan Ma, Chenhao Cheng, Reynold |
| author_facet | Qu, Ge Li, Jinyang Qin, Bowen Li, Xiaolong Huo, Nan Ma, Chenhao Cheng, Reynold |
| contents | Current self-correction approaches in text-to-SQL face two critical limitations: 1) Conventional self-correction methods rely on recursive self-calls of LLMs, resulting in multiplicative computational overhead, and 2) LLMs struggle to implement effective error detection and correction for declarative SQL queries, as they fail to demonstrate the underlying reasoning path. In this work, we propose SHARE, an SLM-based Hierarchical Action corREction assistant that enables LLMs to perform more precise error localization and efficient correction. SHARE orchestrates three specialized Small Language Models (SLMs) in a sequential pipeline, where it first transforms declarative SQL queries into stepwise action trajectories that reveal underlying reasoning, followed by a two-phase granular refinement. We further propose a novel hierarchical self-evolution strategy for data-efficient training. Experimental results demonstrate that SHARE effectively enhances self-correction capabilities while proving robust across various LLMs. Furthermore, our comprehensive analysis shows that SHARE maintains strong performance even in low-resource training settings, which is particularly valuable for text-to-SQL applications with data privacy constraints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00391 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL Qu, Ge Li, Jinyang Qin, Bowen Li, Xiaolong Huo, Nan Ma, Chenhao Cheng, Reynold Computation and Language Current self-correction approaches in text-to-SQL face two critical limitations: 1) Conventional self-correction methods rely on recursive self-calls of LLMs, resulting in multiplicative computational overhead, and 2) LLMs struggle to implement effective error detection and correction for declarative SQL queries, as they fail to demonstrate the underlying reasoning path. In this work, we propose SHARE, an SLM-based Hierarchical Action corREction assistant that enables LLMs to perform more precise error localization and efficient correction. SHARE orchestrates three specialized Small Language Models (SLMs) in a sequential pipeline, where it first transforms declarative SQL queries into stepwise action trajectories that reveal underlying reasoning, followed by a two-phase granular refinement. We further propose a novel hierarchical self-evolution strategy for data-efficient training. Experimental results demonstrate that SHARE effectively enhances self-correction capabilities while proving robust across various LLMs. Furthermore, our comprehensive analysis shows that SHARE maintains strong performance even in low-resource training settings, which is particularly valuable for text-to-SQL applications with data privacy constraints. |
| title | SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.00391 |