SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL

TL;DR

SHARE introduces a hierarchical, multi-model approach to improve error detection and correction in text-to-SQL tasks, reducing computational costs and enhancing performance, especially in low-resource scenarios.

Contribution

The paper presents SHARE, a novel SLM-based hierarchical correction framework that outperforms existing methods in accuracy and efficiency for text-to-SQL error correction.

Findings

Enhances self-correction accuracy across various LLMs.

Maintains robustness in low-resource training settings.

Reduces computational overhead compared to recursive LLM self-calls.

Abstract

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.