.png){kind=icon}
返回
XiYan-SQL: A Novel Multi-Generator Framework for Text-to-SQL
.png){kind=icon}
PRE
AI
DOI：10.1109/TKDE.2026.3657851.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
To leverage the advantages of LLM in addressing challenges in the Text-to-SQL task, we present XiYan-SQL, an innovative framework effectively generating and utilizing multiple SQL candidates. It consists of three components: 1) a Schema Filter module filtering and obtaining multiple relevant schemas; 2) a multi-generator ensemble approach generating multiple high-quality and diverse SQL queries; 3) a selection model with a candidate reorganization strategy implemented to obtain the optimal SQL query. Specifically, for the multi-generator ensemble, we employ a multi-task fine-tuning strategy to enhance the capabilities of SQL generation models for the intrinsic alignment between SQL and text, and construct multiple generation models with distinct generation styles by fine-tuning across different SQL formats. The experimental results and comprehensive analysis demonstrate the effectiveness and robustness of our framework. Overall, XiYan-SQL achieves a new SOTA performance of 75.63% on the notable BIRD benchmark, surpassing all previous methods. It also attains SOTA performance on the Spider test set with an accuracy of 89.65%.
Keyword:
Generation
Text-to-SQL
multiple model ensemble
LLM fine-tuning strategy
期刊
IF:
10.4
论文数:
6.9K
被引数:
3.2W
机构
引用论文
.png){kind=icon}
分享收藏DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-CorrectionDIN-SQL：具有自修正功能的文本到SQL的上下文分解学习
PREAI
分享收藏
查看更多内容