PET-SQL: A Prompt-enhanced Two-stage Text-to-SQL Framework with Cross-consistency

arXiv:2403.09732v1 Announce Type: new
Abstract: Recent advancements in Text-to-SQL (Text2SQL) emphasize stimulating the large language models (LLM) on in-context learning, achieving significant results. Nevertheless, they face challenges when dealing with verbose database information and complex user intentions. This paper presents a two-stage framework to enhance the performance of current LLM-based natural language to SQL systems. We first introduce a novel prompt representation, called reference-enhanced representation, which includes schema information and randomly sampled cell values from tables to instruct LLMs in …

abstract arxiv challenges context cs.ai cs.cl current database face framework in-context learning information language language models large language large language models llm natural natural language paper performance pet prompt results sql stage text text-to-sql type