@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2025-learning">
<titleInfo>
<title>Learning SQL Like a Human: Structure-Aware Curriculum Learning for Text-to-SQL Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaohu</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizhen</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuntao</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">zhu-etal-2025-learning</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.190/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>3545</start>
<end>3559</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning SQL Like a Human: Structure-Aware Curriculum Learning for Text-to-SQL Generation
%A Zhu, Xiaohu
%A Li, Qian
%A Cui, Lizhen
%A Du, Yuntao
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F zhu-etal-2025-learning
%X 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.
%U https://aclanthology.org/2025.findings-emnlp.190/
%P 3545-3559
Markdown (Informal)
[Learning SQL Like a Human: Structure-Aware Curriculum Learning for Text-to-SQL Generation](https://aclanthology.org/2025.findings-emnlp.190/) (Zhu et al., Findings 2025)
ACL