IEEE

AES-SQL: Text-to-SQL Based on Adaptive Prompting and Intelligent Example Selection

Abstract: Large Language Models have greatly enhanced the Text-to-SQL task. In this paper, we propose AES-SQL, an LLM-based approach based on few-shot Learning. We adjust the structure of the adaptive ...
IEEE

PaVeRL-SQL: Text–to–SQL via Partial–Match Rewards and Verbal Reinforcement Learning

Abstract: Text–to–SQL models allow users to interact with a database more easily by generating executable SQL statements from natural–language questions. Despite recent successes on simpler databases ...