TL;DR
RetrySQL introduces a self-correcting training method for text-to-SQL models using retry data, significantly improving accuracy and enabling open-source models to compete with larger proprietary systems.
Contribution
The paper presents a novel training approach with retry data for self-correcting text-to-SQL models, demonstrating improved accuracy and the importance of full-parameter pre-training.
Findings
Up to 4 percentage points improvement in execution accuracy.
Self-correcting behavior is learned through retry training.
Open-source models can match proprietary models in accuracy.
Abstract
The text-to-SQL task is an active challenge in Natural Language Processing. Many existing solutions focus on using black-box language models extended with specialized components within customized end-to-end text-to-SQL pipelines. While these solutions use both closed-source proprietary language models and coding-oriented open-source models, there is a lack of research regarding SQL-specific generative models. At the same time, recent advancements in self-correcting generation strategies show promise for improving the capabilities of existing architectures. The application of these concepts to the text-to-SQL task remains unexplored. In this paper, we introduce RetrySQL, a new approach to training text-to-SQL generation models. We prepare reasoning steps for reference SQL queries and then corrupt them to create retry data that contains both incorrect and corrected steps, divided with a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
