@inproceedings{pourreza-rafiei-2024-dts,
title = "{DTS}-{SQL}: Decomposed Text-to-{SQL} with Small Large Language Models",
author = "Pourreza, Mohammadreza and
Rafiei, Davood",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.481",
pages = "8212--8220",
abstract = "Leading models for the text-to-SQL task heavily rely on proprietary Large Language Models (LLMs), posing concerns over data privacy. Closing the performance gap between small open-source models and large proprietary models is crucial to mitigate this reliance. To this end, we introduce a novel two-stage fine-tuning approach that decomposes the task into two simpler tasks. Through comprehensive evaluation on three large cross-domain datasets and two small LLMs, we show that this approach improves execution accuracy by 3 to 7 percent, effectively aligning the performance of open-source models with their proprietary counterparts. Our proposed method has achieved 60.31{\%} execution accuracy on Bird hold-out test set, which is the highest performance among methods using 7B parameter models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pourreza-rafiei-2024-dts">
<titleInfo>
<title>DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammadreza</namePart>
<namePart type="family">Pourreza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davood</namePart>
<namePart type="family">Rafiei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Leading models for the text-to-SQL task heavily rely on proprietary Large Language Models (LLMs), posing concerns over data privacy. Closing the performance gap between small open-source models and large proprietary models is crucial to mitigate this reliance. To this end, we introduce a novel two-stage fine-tuning approach that decomposes the task into two simpler tasks. Through comprehensive evaluation on three large cross-domain datasets and two small LLMs, we show that this approach improves execution accuracy by 3 to 7 percent, effectively aligning the performance of open-source models with their proprietary counterparts. Our proposed method has achieved 60.31% execution accuracy on Bird hold-out test set, which is the highest performance among methods using 7B parameter models.</abstract>
<identifier type="citekey">pourreza-rafiei-2024-dts</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.481</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>8212</start>
<end>8220</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models
%A Pourreza, Mohammadreza
%A Rafiei, Davood
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F pourreza-rafiei-2024-dts
%X Leading models for the text-to-SQL task heavily rely on proprietary Large Language Models (LLMs), posing concerns over data privacy. Closing the performance gap between small open-source models and large proprietary models is crucial to mitigate this reliance. To this end, we introduce a novel two-stage fine-tuning approach that decomposes the task into two simpler tasks. Through comprehensive evaluation on three large cross-domain datasets and two small LLMs, we show that this approach improves execution accuracy by 3 to 7 percent, effectively aligning the performance of open-source models with their proprietary counterparts. Our proposed method has achieved 60.31% execution accuracy on Bird hold-out test set, which is the highest performance among methods using 7B parameter models.
%U https://aclanthology.org/2024.findings-emnlp.481
%P 8212-8220
Markdown (Informal)
[DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models](https://aclanthology.org/2024.findings-emnlp.481) (Pourreza & Rafiei, Findings 2024)
ACL