SQLfuse：通过全面的LLM协同增强文本到SQL性能
SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergy
AI总结：
SQLfuse通过集成开源LLM与模式挖掘、模式链接、SQL生成及评论四大模块，提升文本到SQL转换的准确性与可用性，并在Spider基准上取得领先表现。
摘要：
文本到SQL转换是一项关键创新，简化了从复杂SQL到直观自然语言查询的过渡，鉴于SQL在就业市场各种角色中的普及，这一点尤为重要。GPT-3.5和GPT-4等大型语言模型（LLMs）的兴起极大地推进了这一领域，提供了改进的自然语言理解和生成细致SQL语句的能力。然而，开源LLMs在文本到SQL应用中的潜力仍未得到充分探索，许多框架未能充分利用其全部能力，特别是在处理复杂数据库查询和纳入反馈以进行迭代优化方面。针对这些局限性，本文介绍了SQLfuse，一个将开源LLMs与一套工具集成的稳健系统，以增强文本到SQL转换的准确性和可用性。SQLfuse包含四个模块：模式挖掘、模式链接、SQL生成和SQL评论模块，不仅生成SQL查询，还持续提升其质量。SQLfuse在Spider排行榜上的领先表现以及蚂蚁集团的部署，展示了开源LLMs在多样化业务场景中的实际价值。
英文摘要：
Text-to-SQL conversion is a critical innovation, simplifying the transition from complex SQL to intuitive natural language queries, especially significant given SQL's prevalence in the job market across various roles. The rise of Large Language Models (LLMs) like GPT-3.5 and GPT-4 has greatly advanced this field, offering improved natural language understanding and the ability to generate nuanced SQL statements. However, the potential of open-source LLMs in Text-to-SQL applications remains underexplored, with many frameworks failing to leverage their full capabilities, particularly in handling complex database queries and incorporating feedback for iterative refinement. Addressing these limitations, this paper introduces SQLfuse, a robust system integrating open-source LLMs with a suite of tools to enhance Text-to-SQL translation's accuracy and usability. SQLfuse features four modules: schema mining, schema linking, SQL generation, and a SQL critic module, to not only generate but also continuously enhance SQL query quality. Demonstrated by its leading performance on the Spider Leaderboard and deployment by Ant Group, SQLfuse showcases the practical merits of open-source LLMs in diverse business contexts.
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。
