RH-SQL: Refined Schema and Hardness Prompt for Text-to-SQL

TL;DR

This paper introduces RH-SQL, a cost-effective Text-to-SQL method using refined schema and hardness prompts, achieving high accuracy on the Spider dataset with large language models.

Contribution

It proposes a novel approach that reduces storage and training costs in Text-to-SQL by filtering schema relevance and leveraging query hardness prompts, applicable to any seq2seq LM.

Findings

Achieved 82.6% execution accuracy on Spider dataset

Reduced storage and training costs compared to existing methods

Applicable to various sequence-to-sequence language models

Abstract

Text-to-SQL is a technology that converts natural language queries into the structured query language SQL. A novel research approach that has recently gained attention focuses on methods based on the complexity of SQL queries, achieving notable performance improvements. However, existing methods entail significant storage and training costs, which hampers their practical application. To address this issue, this paper introduces a method for Text-to-SQL based on Refined Schema and Hardness Prompt. By filtering out low-relevance schema information with a refined schema and identifying query hardness through a Language Model (LM) to form prompts, this method reduces storage and training costs while maintaining performance. It's worth mentioning that this method is applicable to any sequence-to-sequence (seq2seq) LM. Our experiments on the Spider dataset, specifically with large-scale LMs, achieved an exceptional Execution accuracy (EX) of 82.6%, demonstrating the effectiveness and greater suitability of our method for real-world applications.