@inproceedings{shi-etal-2025-gen,
title = "Gen-{SQL}: Efficient Text-to-{SQL} By Bridging Natural Language Question And Database Schema With Pseudo-Schema",
author = "Shi, Jie and
Xu, Bo and
Liang, Jiaqing and
Xiao, Yanghua and
Chen, Jia and
Xie, Chenhao and
Wang, Peng and
Wang, Wei",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.256/",
pages = "3794--3807",
abstract = "With the prevalence of Large Language Models (LLMs), recent studies have shifted paradigms and leveraged LLMs to tackle the challenging task of Text-to-SQL. Because of the complexity of real world databases, previous works adopt the retrieve-then-generate framework to retrieve relevant database schema and then to generate the SQL query. However, efficient embedding-based retriever suffers from lower retrieval accuracy, and more accurate LLM-based retriever is far more expensive to use, which hinders their applicability for broader applications. To overcome this issue, this paper proposes Gen-SQL, a novel generate-ground-regenerate framework, where we exploit prior knowledge from the LLM to enhance embedding-based retriever and reduce cost. Experiments on several datasets are conducted to demonstrate the effectiveness and scalability of our proposed method. We release our code and data at https://github.com/jieshi10/gensql."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2025-gen">
<titleInfo>
<title>Gen-SQL: Efficient Text-to-SQL By Bridging Natural Language Question And Database Schema With Pseudo-Schema</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">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">Chenhao</namePart>
<namePart type="family">Xie</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>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the prevalence of Large Language Models (LLMs), recent studies have shifted paradigms and leveraged LLMs to tackle the challenging task of Text-to-SQL. Because of the complexity of real world databases, previous works adopt the retrieve-then-generate framework to retrieve relevant database schema and then to generate the SQL query. However, efficient embedding-based retriever suffers from lower retrieval accuracy, and more accurate LLM-based retriever is far more expensive to use, which hinders their applicability for broader applications. To overcome this issue, this paper proposes Gen-SQL, a novel generate-ground-regenerate framework, where we exploit prior knowledge from the LLM to enhance embedding-based retriever and reduce cost. Experiments on several datasets are conducted to demonstrate the effectiveness and scalability of our proposed method. We release our code and data at https://github.com/jieshi10/gensql.</abstract>
<identifier type="citekey">shi-etal-2025-gen</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.256/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>3794</start>
<end>3807</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Gen-SQL: Efficient Text-to-SQL By Bridging Natural Language Question And Database Schema With Pseudo-Schema
%A Shi, Jie
%A Xu, Bo
%A Liang, Jiaqing
%A Xiao, Yanghua
%A Chen, Jia
%A Xie, Chenhao
%A Wang, Peng
%A Wang, Wei
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F shi-etal-2025-gen
%X With the prevalence of Large Language Models (LLMs), recent studies have shifted paradigms and leveraged LLMs to tackle the challenging task of Text-to-SQL. Because of the complexity of real world databases, previous works adopt the retrieve-then-generate framework to retrieve relevant database schema and then to generate the SQL query. However, efficient embedding-based retriever suffers from lower retrieval accuracy, and more accurate LLM-based retriever is far more expensive to use, which hinders their applicability for broader applications. To overcome this issue, this paper proposes Gen-SQL, a novel generate-ground-regenerate framework, where we exploit prior knowledge from the LLM to enhance embedding-based retriever and reduce cost. Experiments on several datasets are conducted to demonstrate the effectiveness and scalability of our proposed method. We release our code and data at https://github.com/jieshi10/gensql.
%U https://aclanthology.org/2025.coling-main.256/
%P 3794-3807
Markdown (Informal)
[Gen-SQL: Efficient Text-to-SQL By Bridging Natural Language Question And Database Schema With Pseudo-Schema](https://aclanthology.org/2025.coling-main.256/) (Shi et al., COLING 2025)
ACL
- Jie Shi, Bo Xu, Jiaqing Liang, Yanghua Xiao, Jia Chen, Chenhao Xie, Peng Wang, and Wei Wang. 2025. Gen-SQL: Efficient Text-to-SQL By Bridging Natural Language Question And Database Schema With Pseudo-Schema. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3794–3807, Abu Dhabi, UAE. Association for Computational Linguistics.