@inproceedings{park-etal-2026-resql,
title = "{R}e{SQL}: Self-Improving Framework for Reasoning-Aware Text-to-{SQL} Dataset Generation",
author = "Park, Minjun and
Seong, Yongju and
Sim, Myoseop and
Min, Kyungkoo and
Choi, Stanley Jungkyu",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1677/",
pages = "33582--33602",
ISBN = "979-8-89176-395-1",
abstract = "Recent advances in Text-to-SQL have greatly benefited from large language models, yet small and medium-sized models still suffer from frequent execution errors and limited self-correction ability. We present ReSQL (Retrieval-augmented error reasoning for Text-to-SQL), a self-improving framework that generates and learns from its own error-reasoning dataset, enabling models to autonomously refine their SQL generation and correction capabilities. ReSQL combines feedback-driven fine-tuning with retrieval-based inference: it gathers model-generated errors, analyzes them through structured feedback prompts, and retrieves relevant correction examples during inference. This unified approach allows models to internalize robust error-reasoning patterns and dynamically apply them to unseen queries. Experimental results on the SPIDER and BIRD benchmarks show that ReSQL substantially improves execution accuracy and self-correction ability over strong baselines, achieving competitive performance with much larger proprietary models such as GPT-4. Our findings highlight ReSQL as a promising step toward self-improving, reasoning-aware Text-to-SQL systems that can continually enhance their reliability and interpretability without external supervision. All code and generated reasoning datasets are available to facilitate application to open-source LLMs and reproducible baseline training."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2026-resql">
<titleInfo>
<title>ReSQL: Self-Improving Framework for Reasoning-Aware Text-to-SQL Dataset Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minjun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongju</namePart>
<namePart type="family">Seong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Myoseop</namePart>
<namePart type="family">Sim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyungkoo</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stanley</namePart>
<namePart type="given">Jungkyu</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Recent advances in Text-to-SQL have greatly benefited from large language models, yet small and medium-sized models still suffer from frequent execution errors and limited self-correction ability. We present ReSQL (Retrieval-augmented error reasoning for Text-to-SQL), a self-improving framework that generates and learns from its own error-reasoning dataset, enabling models to autonomously refine their SQL generation and correction capabilities. ReSQL combines feedback-driven fine-tuning with retrieval-based inference: it gathers model-generated errors, analyzes them through structured feedback prompts, and retrieves relevant correction examples during inference. This unified approach allows models to internalize robust error-reasoning patterns and dynamically apply them to unseen queries. Experimental results on the SPIDER and BIRD benchmarks show that ReSQL substantially improves execution accuracy and self-correction ability over strong baselines, achieving competitive performance with much larger proprietary models such as GPT-4. Our findings highlight ReSQL as a promising step toward self-improving, reasoning-aware Text-to-SQL systems that can continually enhance their reliability and interpretability without external supervision. All code and generated reasoning datasets are available to facilitate application to open-source LLMs and reproducible baseline training.</abstract>
<identifier type="citekey">park-etal-2026-resql</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1677/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>33582</start>
<end>33602</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReSQL: Self-Improving Framework for Reasoning-Aware Text-to-SQL Dataset Generation
%A Park, Minjun
%A Seong, Yongju
%A Sim, Myoseop
%A Min, Kyungkoo
%A Choi, Stanley Jungkyu
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F park-etal-2026-resql
%X Recent advances in Text-to-SQL have greatly benefited from large language models, yet small and medium-sized models still suffer from frequent execution errors and limited self-correction ability. We present ReSQL (Retrieval-augmented error reasoning for Text-to-SQL), a self-improving framework that generates and learns from its own error-reasoning dataset, enabling models to autonomously refine their SQL generation and correction capabilities. ReSQL combines feedback-driven fine-tuning with retrieval-based inference: it gathers model-generated errors, analyzes them through structured feedback prompts, and retrieves relevant correction examples during inference. This unified approach allows models to internalize robust error-reasoning patterns and dynamically apply them to unseen queries. Experimental results on the SPIDER and BIRD benchmarks show that ReSQL substantially improves execution accuracy and self-correction ability over strong baselines, achieving competitive performance with much larger proprietary models such as GPT-4. Our findings highlight ReSQL as a promising step toward self-improving, reasoning-aware Text-to-SQL systems that can continually enhance their reliability and interpretability without external supervision. All code and generated reasoning datasets are available to facilitate application to open-source LLMs and reproducible baseline training.
%U https://aclanthology.org/2026.findings-acl.1677/
%P 33582-33602
Markdown (Informal)
[ReSQL: Self-Improving Framework for Reasoning-Aware Text-to-SQL Dataset Generation](https://aclanthology.org/2026.findings-acl.1677/) (Park et al., Findings 2026)
ACL