Text to SQL
Text-to-SQL research aims to automatically translate natural language queries into structured SQL queries, enabling non-experts to access and analyze data in relational databases. Current research heavily utilizes large language models (LLMs), focusing on improving accuracy through techniques like chain-of-thought prompting, multi-agent systems, and data augmentation strategies to address challenges such as complex schemas and ambiguous queries. This field is significant because it democratizes data access, impacting various sectors by streamlining data analysis and reducing the reliance on specialized SQL knowledge. Furthermore, ongoing work addresses the need for more robust evaluation metrics and benchmarks that reflect real-world complexities, particularly within enterprise settings.
Papers
Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm
Yuanzhen Xie, Xinzhou Jin, Tao Xie, MingXiong Lin, Liang Chen, Chenyun Yu, Lei Cheng, ChengXiang Zhuo, Bo Hu, Zang Li
MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL
Xuanliang Zhang, Dingzirui Wang, Longxu Dou, Qingfu Zhu, Wanxiang Che
Improving Demonstration Diversity by Human-Free Fusing for Text-to-SQL
Dingzirui Wang, Longxu Dou, Xuanliang Zhang, Qingfu Zhu, Wanxiang Che