arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.10593cs.AIcs.DBcs.IR
收藏

QDA-SQL:用于多轮文本到SQL的问题增强对话扩充

QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQL

School of Cyberspace Science Harbin Institute of Technology Harbin, China(网络空间科学学院 哈尔滨工业大学 哈尔滨,中国);School of Computer Science(计算机科学学院);Technology Harbin University of Science(技术 哈尔滨理工大学);School of Cyberspace Science Harbin Institute of Technology, Shenzhen Shenzhen, China(网络空间科学学院 哈尔滨工业大学深圳 哈尔滨,中国)

Yinggang Sun, Ziming Guo, Haining Yu, Chuanyi Liu, Xiang Li, Bingxuan Wang, Xiangzhan Yu, Tiancheng Zhao

AI总结:

该研究针对多轮文本到SQL任务中微调模型面临的问题,提出QDA-SQL数据扩充方法,利用大语言模型生成多轮问答对,并引入验证和校正机制,提升了微调模型在SQL语句准确性及处理复杂问题上的能力。

摘要:

针对特定领域任务微调大语言模型在文本到SQL任务中取得了巨大成功。然而,这些微调模型在多轮文本到SQL任务中常因问题模糊或无法回答而面临挑战。为解决此问题,我们提出了一种名为QDA-SQL的新型数据扩充方法,它使用大语言模型生成多种类型的多轮问答对。在QDA-SQL中,我们引入了一种结合验证和校正机制的方法来处理复杂的多轮文本到SQL任务。实验结果表明,QDA-SQL能使微调模型在SQL语句准确性上表现出更高性能,并增强其处理多轮文本到SQL任务中复杂、无法回答问题的能力。生成脚本和测试集已在该https URL发布。

英文摘要:

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

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑