@inproceedings{gao-etal-2026-msi,
title = "{MSI}-{SQL}: Unleashing Data Potential of Large Language Models for Text-to-{SQL} via Multi-Task Self-Iterative Generation",
author = "Gao, Li and
Wang, Zixuan and
Peng, Boci and
Nie, Mingjun and
Luo, Huan and
Gan, Chun",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2390/",
pages = "51372--51382",
ISBN = "979-8-89176-462-0",
abstract = "Text-to-SQL parsing increasingly relies on high-quality Chain-of-Thought (CoT) data to train specialized models. However, eliciting accurate reasoning paths for complex queries remains a formidable challenge, causing existing methods to suffer from severe data underutilization and fragile free-form generation. To systematically resolve these issues, we propose MSI-SQL, a Multi-task Self-Iterative framework that enhances both data quantity and quality. To expand data scale, we introduce a verification-based self-iterative loop that progressively conquers difficult queries. To ensure reasoning stability, we design a masked SQL completion auxiliary task that serves as a structural anchor, explicitly constraining the CoT generation space. Coupled with a novel mask-augmented soft self-consistency mechanism during inference, evaluations on the BIRD and Spider benchmarks demonstrate that MSI-SQL establishes a new state-of-the-art for open-source Text-to-SQL parsers."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2026-msi">
<titleInfo>
<title>MSI-SQL: Unleashing Data Potential of Large Language Models for Text-to-SQL via Multi-Task Self-Iterative Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zixuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boci</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingjun</namePart>
<namePart type="family">Nie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chun</namePart>
<namePart type="family">Gan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Text-to-SQL parsing increasingly relies on high-quality Chain-of-Thought (CoT) data to train specialized models. However, eliciting accurate reasoning paths for complex queries remains a formidable challenge, causing existing methods to suffer from severe data underutilization and fragile free-form generation. To systematically resolve these issues, we propose MSI-SQL, a Multi-task Self-Iterative framework that enhances both data quantity and quality. To expand data scale, we introduce a verification-based self-iterative loop that progressively conquers difficult queries. To ensure reasoning stability, we design a masked SQL completion auxiliary task that serves as a structural anchor, explicitly constraining the CoT generation space. Coupled with a novel mask-augmented soft self-consistency mechanism during inference, evaluations on the BIRD and Spider benchmarks demonstrate that MSI-SQL establishes a new state-of-the-art for open-source Text-to-SQL parsers.</abstract>
<identifier type="citekey">gao-etal-2026-msi</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2390/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>51372</start>
<end>51382</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MSI-SQL: Unleashing Data Potential of Large Language Models for Text-to-SQL via Multi-Task Self-Iterative Generation
%A Gao, Li
%A Wang, Zixuan
%A Peng, Boci
%A Nie, Mingjun
%A Luo, Huan
%A Gan, Chun
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F gao-etal-2026-msi
%X Text-to-SQL parsing increasingly relies on high-quality Chain-of-Thought (CoT) data to train specialized models. However, eliciting accurate reasoning paths for complex queries remains a formidable challenge, causing existing methods to suffer from severe data underutilization and fragile free-form generation. To systematically resolve these issues, we propose MSI-SQL, a Multi-task Self-Iterative framework that enhances both data quantity and quality. To expand data scale, we introduce a verification-based self-iterative loop that progressively conquers difficult queries. To ensure reasoning stability, we design a masked SQL completion auxiliary task that serves as a structural anchor, explicitly constraining the CoT generation space. Coupled with a novel mask-augmented soft self-consistency mechanism during inference, evaluations on the BIRD and Spider benchmarks demonstrate that MSI-SQL establishes a new state-of-the-art for open-source Text-to-SQL parsers.
%U https://aclanthology.org/2026.findings-emnlp.2390/
%P 51372-51382
Markdown (Informal)
[MSI-SQL: Unleashing Data Potential of Large Language Models for Text-to-SQL via Multi-Task Self-Iterative Generation](https://aclanthology.org/2026.findings-emnlp.2390/) (Gao et al., Findings 2026)
ACL