KeyInst: Keyword Instruction for Improving SQL Formulation in Text-to-SQL
This work addresses the problem of semantic alignment in text-to-SQL parsing for database querying, representing an incremental advancement by enhancing existing LLM-based methods with keyword guidance.
The paper tackles the challenge of generating SQL queries that are semantically aligned with natural language inputs in text-to-SQL parsing by introducing Keyword Instruction (KeyInst), a method that guides large language models with pivotal SQL keywords, resulting in significant improvements over existing prompting techniques as demonstrated on benchmarks like StrucQL.
Text-to-SQL parsing involves the translation of natural language queries (NLQs) into their corresponding SQL commands. A principal challenge within this domain is the formulation of SQL queries that are not only syntactically correct but also semantically aligned with the natural language input. However, the intrinsic disparity between the NLQ and the SQL poses a significant challenge. In this research, we introduce Keyword Instruction (KeyInst), a novel method designed to enhance SQL formulation by Large Language Models (LLMs). KeyInst essentially provides guidance on pivotal SQL keywords likely to be part of the final query, thus facilitates a smoother SQL query formulation process. We explore two strategies for integrating KeyInst into Text-to-SQL parsing: a pipeline strategy and a single-pass strategy. The former first generates KeyInst for question, which are then used to prompt LLMs. The latter employs a fine-tuned model to concurrently generate KeyInst and SQL in one step. We developed StrucQL, a benchmark specifically designed for the evaluation of SQL formulation. Extensive experiments on StrucQL and other benchmarks demonstrate that KeyInst significantly improves upon the existing Text-to-SQL prompting techniques.