DAC: Decomposed Automation Correction for Text-to-SQL

TL;DR

This paper introduces DAC, a decomposed correction method for text-to-SQL tasks that improves accuracy by breaking down SQL correction into entity linking and skeleton parsing, outperforming direct correction approaches.

Contribution

The paper proposes a novel decomposed correction approach (DAC) that enhances text-to-SQL performance by simplifying mistake detection and correction through task decomposition.

Findings

DAC improves performance by 3.7% on average across datasets.

Decomposed correction outperforms direct correction in accuracy.

Experimental results validate the effectiveness of the proposed method.

Abstract

Text-to-SQL is an important task that helps people obtain information from databases by automatically generating SQL queries. Considering the brilliant performance, approaches based on Large Language Models (LLMs) become the mainstream for text-to-SQL. Among these approaches, automated correction is an effective approach that further enhances performance by correcting the mistakes in the generated results. The existing correction methods require LLMs to directly correct with generated SQL, while previous research shows that LLMs do not know how to detect mistakes, leading to poor performance. Therefore, in this paper, we propose to employ the decomposed correction to enhance text-to-SQL performance. We first demonstrate that decomposed correction outperforms direct correction since detecting and fixing mistakes with the results of the decomposed sub-tasks is easier than with SQL. Based on this analysis, we introduce Decomposed Automation Correction (DAC), which corrects SQL by decomposing text-to-SQL into entity linking and skeleton parsing. DAC first generates the entity and skeleton corresponding to the question and then compares the differences between the initial SQL and the generated entities and skeleton as feedback for correction. Experimental results show that our method improves performance by $3.7\%$ on average of Spider, Bird, and KaggleDBQA compared with the baseline method, demonstrating the effectiveness of DAC.