Fine-tuning large language models (LLMs) for specific domain tasks has achieved great success in Text-to-SQL tasks. However, these fine-tuned models often face challenges with multi-turn Text-to-SQL tasks caused by ambiguous or unanswerable questions. It is desired to enhance LLMs to handle multiple types of questions in multi-turn Text-to-SQL tasks. To address this, we propose a novel data augmentation method, called QDA-SQL, which generates multiple types of multi-turn Q\&A pairs using LLMs. In QDA-SQL, we introduce a method incorporating validation and correction mechanisms to handle complex multi-turn Text-to-SQL tasks. Experimental results demonstrate that QDA-SQL enables fine-tuned models to exhibit higher performance on SQL statement accuracy and enhances their ability to handle complex, unanswerable questions in multi-turn Text-to-SQL tasks. The generation script and test set are released at https://github.com/mcxiaoxiao/QDA-SQL
@article{arxiv.2406.10593,
title = {QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQL},
author = {Yinggang Sun and Ziming Guo and Haining Yu and Chuanyi Liu and Xiang Li and Bingxuan Wang and Xiangzhan Yu and Tiancheng Zhao},
journal= {arXiv preprint arXiv:2406.10593},
year = {2024}
}