@inproceedings{zhu-etal-2025-learning,
    title = "Learning {SQL} Like a Human: Structure-Aware Curriculum Learning for Text-to-{SQL} Generation",
    author = "Zhu, Xiaohu  and
      Li, Qian  and
      Cui, Lizhen  and
      Du, Yuntao",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.190/",
    doi = "10.18653/v1/2025.findings-emnlp.190",
    pages = "3545--3559",
    ISBN = "979-8-89176-335-7",
    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."
}