SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL
This addresses inefficiencies in text-to-SQL systems for database query applications, offering a more data-efficient solution, though it is incremental as it builds on existing self-correction methods.
The paper tackles the problem of inefficient and ineffective self-correction in text-to-SQL by proposing SHARE, a hierarchical assistant using small language models, which enhances error localization and correction while reducing computational overhead, achieving robust performance across various LLMs and in low-resource settings.
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.