让AI通过人类反馈持续学习数据库知识，提升文本转SQL的准确率。
Continual Learning of Domain Knowledge from Human Feedback in Text-to-SQL
- 用人类反馈不断优化SQL生成，将经验存入结构化记忆。
- 在BIRD基准上，带记忆的智能体准确率显著提升，错误减少37%。
- 适合需要持续改进的智能数据库助手研发者。
大型语言模型虽能将自然语言问题转为SQL，但在特定数据库模式和隐性领域知识上表现不佳。本文提出一种基于人类反馈的文本转SQL持续学习框架：学习智能体接收自然语言反馈以修正查询，并将揭示的知识提炼后存入结构化记忆，实现未来任务复用。通过设计并评估多种智能体架构，实验在BIRD基准开发集上显示，引入记忆机制的智能体（尤其是过程式智能体）借助人机协同反馈，显著提升执行准确率并降低错误率。结果表明，将隐性人类专长转化为可复用知识至关重要，为更适应、更懂领域的文本转SQL系统提供了持续学习路径。
原文摘要 · Abstract (English)
Large Language Models (LLMs) can generate SQL queries from natural language questions but struggle with database-specific schemas and tacit domain knowledge. We introduce a framework for continual learning from human feedback in text-to-SQL, where a learning agent receives natural language feedback to refine queries and distills the revealed knowledge for reuse on future tasks. This distilled knowledge is stored in a structured memory, enabling the agent to improve execution accuracy over time. We design and evaluate multiple variations of a learning agent architecture that vary in how they capture and retrieve past experiences. Experiments on the BIRD benchmark Dev set show that memory-augmented agents, particularly the Procedural Agent, achieve significant accuracy gains and error reduction by leveraging human-in-the-loop feedback. Our results highlight the importance of transforming tacit human expertise into reusable knowledge, paving the way for more adaptive, domain-aware text-to-SQL systems that continually learn from a human-in-the-loop.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。