Learning SQL Like a Human: Structure-Aware Curriculum Learning for Text-to-SQL Generation

ACL ARR 2025 May Submission7506 Authors

Abstract: The Text-to-SQL capabilities of large language allow users to interact with databases using natural language. While current models struggle with handling complex queries, especially involving multi-table joins and reasoning. To address this gap, we propose to construct a model, namely SAC-SQL, with synthetic training samples followed by a structure-aware curriculum learning framework for enhancing SQL generation. Our approach begins with a supervised fine-tuning (SFT) stage, where we train open-source models on a synthetically constructed, cross-domain SQL dataset with diverse structural patterns. Moreover, we introduce a unified structure difficulty scoring function to partition the training samples into non-overlapping curriculum phases, guiding the model progressively learning from simpler to more complex SQL structures. Extensive experiments are conducted and the results show that SAC-SQL achieves better results than the baselines, and significantly narrows the performance gap between open-source and close-source models on Spider and Bird benchmarks.

Paper Type: Long

Research Area: Language Modeling

Research Area Keywords: Text to SQL, Language Modeling, Large Language Model, Curriculum Learning

Contribution Types: Model analysis & interpretability, Publicly available software and/or pre-trained models

Languages Studied: English

Submission Number: 7506