SAFE-SQL：自我增強上下文學習與細粒度示例選擇，適用於文本到SQL

SAFE-SQL: Self-Augmented In-Context Learning with Fine-grained Example Selection for Text-to-SQL

February 17, 2025

作者: Jimin Lee, Ingeol Baek, Byeongjeong Kim, Hwanhee Lee

cs.AI

摘要

Text-to-SQL 旨在將自然語言問題轉換為可執行的 SQL 查詢。雖然先前的方法，如骨架遮罩選擇，通過檢索類似的訓練示例來引導大型語言模型（LLMs），已經展示出強大的性能，但在現實情況下，這些示例不可用時，它們會遇到困難。為了克服這一限制，我們提出了一種名為「自我增強上下文學習與精細篩選示例的 Text-to-SQL（SAFE-SQL）」的新框架，通過生成和篩選自我增強示例來改進 SQL 生成。SAFE-SQL 首先提示一個LLM生成多個與測試輸入相關的 Text-to-SQL 示例。然後，SAFE-SQL 通過三個相關性評估篩選這些示例，構建高質量的上下文學習示例。使用自生成的示例，SAFE-SQL 超越了先前的零-shot 和少-shot Text-to-SQL 框架，實現更高的執行準確性。值得注意的是，我們的方法在額外困難和未知情況下提供了額外的性能增益，而傳統方法通常失敗。

English

Text-to-SQL aims to convert natural language questions into executable SQL queries. While previous approaches, such as skeleton-masked selection, have demonstrated strong performance by retrieving similar training examples to guide large language models (LLMs), they struggle in real-world scenarios where such examples are unavailable. To overcome this limitation, we propose Self-Augmentation in-context learning with Fine-grained Example selection for Text-to-SQL (SAFE-SQL), a novel framework that improves SQL generation by generating and filtering self-augmented examples. SAFE-SQL first prompts an LLM to generate multiple Text-to-SQL examples relevant to the test input. Then SAFE-SQL filters these examples through three relevance assessments, constructing high-quality in-context learning examples. Using self-generated examples, SAFE-SQL surpasses the previous zero-shot, and few-shot Text-to-SQL frameworks, achieving higher execution accuracy. Notably, our approach provides additional performance gains in extra hard and unseen scenarios, where conventional methods often fail.