QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQL
Yinggang Sun, Ziming Guo, Haining Yu, Chuanyi Liu, Xiang Li, Bingxuan, Wang, Xiangzhan Yu, Tiancheng Zhao

TL;DR
QDA-SQL is a novel data augmentation approach that improves multi-turn Text-to-SQL performance by generating diverse question-answer pairs and handling complex, unanswerable questions through validation and correction mechanisms.
Contribution
The paper introduces QDA-SQL, a new data augmentation method that enhances LLMs' ability to manage multi-turn, complex, and unanswerable questions in Text-to-SQL tasks.
Findings
Improved SQL statement accuracy on multi-turn tasks
Enhanced handling of unanswerable questions
Effective augmentation with validation and correction
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsService-Oriented Architecture and Web Services · Speech and dialogue systems · Robotics and Automated Systems
MethodsSparse Evolutionary Training
