@inproceedings{shi-etal-2025-dialect,
title = "Dialect-{SQL}: An Adaptive Framework for Bridging the Dialect Gap in Text-to-{SQL}",
author = "Shi, Jie and
Cao, Xi and
Xu, Bo and
Liang, Jiaqing and
Xiao, Yanghua and
Chen, Jia and
Wang, Peng and
Wang, Wei",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.178/",
doi = "10.18653/v1/2025.emnlp-main.178",
pages = "3604--3619",
ISBN = "979-8-89176-332-6",
abstract = "Text-to-SQL is the task of translating natural language questions into SQL queries based on relational databases. Different databases implement their own SQL dialects, leading to variations in syntax. As a result, SQL queries designed for one database may not execute properly in another, creating a dialect gap. Existing Text-to-SQL research primarily focuses on specific database systems, limiting adaptability to different dialects. This paper proposes a novel adaptive framework called Dialect-SQL, which employs Object Relational Mapping (ORM) code as an intermediate language to bridge this gap. Given a question, we guide Large Language Models (LLMs) to first generate ORM code, which is then parsed into SQL queries targeted for specific databases. However, there is a lack of high-quality Text-to-Code datasets that enable LLMs to effectively generate ORM code. To address this issue, we propose a bootstrapping approach to synthesize ORM code, where verified ORM code is iteratively integrated into a demonstration pool that serves as in-context examples for ORM code generation. Our experiments demonstrate that Dialect-SQL significantly enhances dialect adaptability, outperforming traditional methods that generate SQL queries directly. Our code and data are released at https://github.com/jieshi10/orm-sql."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2025-dialect">
<titleInfo>
<title>Dialect-SQL: An Adaptive Framework for Bridging the Dialect Gap in Text-to-SQL</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaqing</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanghua</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jia</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wang</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>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Text-to-SQL is the task of translating natural language questions into SQL queries based on relational databases. Different databases implement their own SQL dialects, leading to variations in syntax. As a result, SQL queries designed for one database may not execute properly in another, creating a dialect gap. Existing Text-to-SQL research primarily focuses on specific database systems, limiting adaptability to different dialects. This paper proposes a novel adaptive framework called Dialect-SQL, which employs Object Relational Mapping (ORM) code as an intermediate language to bridge this gap. Given a question, we guide Large Language Models (LLMs) to first generate ORM code, which is then parsed into SQL queries targeted for specific databases. However, there is a lack of high-quality Text-to-Code datasets that enable LLMs to effectively generate ORM code. To address this issue, we propose a bootstrapping approach to synthesize ORM code, where verified ORM code is iteratively integrated into a demonstration pool that serves as in-context examples for ORM code generation. Our experiments demonstrate that Dialect-SQL significantly enhances dialect adaptability, outperforming traditional methods that generate SQL queries directly. Our code and data are released at https://github.com/jieshi10/orm-sql.</abstract>
<identifier type="citekey">shi-etal-2025-dialect</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.178</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.178/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>3604</start>
<end>3619</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dialect-SQL: An Adaptive Framework for Bridging the Dialect Gap in Text-to-SQL
%A Shi, Jie
%A Cao, Xi
%A Xu, Bo
%A Liang, Jiaqing
%A Xiao, Yanghua
%A Chen, Jia
%A Wang, Peng
%A Wang, Wei
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F shi-etal-2025-dialect
%X Text-to-SQL is the task of translating natural language questions into SQL queries based on relational databases. Different databases implement their own SQL dialects, leading to variations in syntax. As a result, SQL queries designed for one database may not execute properly in another, creating a dialect gap. Existing Text-to-SQL research primarily focuses on specific database systems, limiting adaptability to different dialects. This paper proposes a novel adaptive framework called Dialect-SQL, which employs Object Relational Mapping (ORM) code as an intermediate language to bridge this gap. Given a question, we guide Large Language Models (LLMs) to first generate ORM code, which is then parsed into SQL queries targeted for specific databases. However, there is a lack of high-quality Text-to-Code datasets that enable LLMs to effectively generate ORM code. To address this issue, we propose a bootstrapping approach to synthesize ORM code, where verified ORM code is iteratively integrated into a demonstration pool that serves as in-context examples for ORM code generation. Our experiments demonstrate that Dialect-SQL significantly enhances dialect adaptability, outperforming traditional methods that generate SQL queries directly. Our code and data are released at https://github.com/jieshi10/orm-sql.
%R 10.18653/v1/2025.emnlp-main.178
%U https://aclanthology.org/2025.emnlp-main.178/
%U https://doi.org/10.18653/v1/2025.emnlp-main.178
%P 3604-3619
Markdown (Informal)
[Dialect-SQL: An Adaptive Framework for Bridging the Dialect Gap in Text-to-SQL](https://aclanthology.org/2025.emnlp-main.178/) (Shi et al., EMNLP 2025)
ACL
- Jie Shi, Xi Cao, Bo Xu, Jiaqing Liang, Yanghua Xiao, Jia Chen, Peng Wang, and Wei Wang. 2025. Dialect-SQL: An Adaptive Framework for Bridging the Dialect Gap in Text-to-SQL. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 3604–3619, Suzhou, China. Association for Computational Linguistics.