Scholarlink

In recent years, research on Text-to-SQL with Large Language Models (LLMs) has mainly focused on enhancing the understanding of database schemas to improve model performance but has overlooked the crucial role that the actual data values stored in the database play in the Text-to-SQL task. Furthermore, insufficient attention has been given to the keywords required for SQL generation and their corresponding condition information. To address this issue, we designed the SSC-SQL framework. By constructing a dynamic fusion mechanism that integrates data values with schema information, this framework effectively bridges the semantic gap between natural language queries and database structures, mitigating mismatches between SQL condition predicates and database schemas. In addition, the framework analyzes SQL syntax structures and query intent to classify user questions. Based on different categories, it applies customized SQL skeleton generation strategies to ensure the stability of SQL keywords and improve the accuracy of cross-table column-value matching. We conducted a systematic evaluation on the Bird benchmark dataset, achieving an execution accuracy of 64.93%, demonstrating the effectiveness of the SSC-SQL framework.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SSC-SQL: A Text-to-SQL Generation Framework with Multi-process Collaboration

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Jiazhuang Yao,
  • Zhao Li,
  • Shiwei Wu,
  • Yiming Zhan,
  • Yang Li

摘要

In recent years, research on Text-to-SQL with Large Language Models (LLMs) has mainly focused on enhancing the understanding of database schemas to improve model performance but has overlooked the crucial role that the actual data values stored in the database play in the Text-to-SQL task. Furthermore, insufficient attention has been given to the keywords required for SQL generation and their corresponding condition information. To address this issue, we designed the SSC-SQL framework. By constructing a dynamic fusion mechanism that integrates data values with schema information, this framework effectively bridges the semantic gap between natural language queries and database structures, mitigating mismatches between SQL condition predicates and database schemas. In addition, the framework analyzes SQL syntax structures and query intent to classify user questions. Based on different categories, it applies customized SQL skeleton generation strategies to ensure the stability of SQL keywords and improve the accuracy of cross-table column-value matching. We conducted a systematic evaluation on the Bird benchmark dataset, achieving an execution accuracy of 64.93%, demonstrating the effectiveness of the SSC-SQL framework.