@inproceedings{gorti-etal-2025-msc,
title = "{MS}c-{SQL}: Multi-Sample Critiquing Small Language Models For Text-To-{SQL} Translation",
author = {Gorti, Satya Krishna and
Gofman, Ilan and
Liu, Zhaoyan and
Wu, Jiapeng and
Vouitsis, No{\"e}l and
Yu, Guangwei and
Cresswell, Jesse C. and
Hosseinzadeh, Rasa},
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.107/",
doi = "10.18653/v1/2025.naacl-long.107",
pages = "2145--2160",
ISBN = "979-8-89176-189-6",
abstract = "Text-to-SQL generation enables non-experts to interact with databases via natural language. Recent advances rely on large closed-source models like GPT-4 that present challenges in accessibility, privacy, and latency. To address these issues, we focus on developing small, efficient, and open-source text-to-SQL models. We demonstrate the benefits of sampling multiple candidate SQL generations and propose our method, MSc-SQL, to critique them using associated metadata. Our sample critiquing model evaluates multiple outputs simultaneously, achieving state-of-the-art performance compared to other open-source models while remaining competitive with larger models at a much lower cost. Full code can be found at github.com/layer6ai-labs/msc-sql."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gorti-etal-2025-msc">
<titleInfo>
<title>MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Satya</namePart>
<namePart type="given">Krishna</namePart>
<namePart type="family">Gorti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilan</namePart>
<namePart type="family">Gofman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoyan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiapeng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noël</namePart>
<namePart type="family">Vouitsis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangwei</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesse</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Cresswell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rasa</namePart>
<namePart type="family">Hosseinzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Text-to-SQL generation enables non-experts to interact with databases via natural language. Recent advances rely on large closed-source models like GPT-4 that present challenges in accessibility, privacy, and latency. To address these issues, we focus on developing small, efficient, and open-source text-to-SQL models. We demonstrate the benefits of sampling multiple candidate SQL generations and propose our method, MSc-SQL, to critique them using associated metadata. Our sample critiquing model evaluates multiple outputs simultaneously, achieving state-of-the-art performance compared to other open-source models while remaining competitive with larger models at a much lower cost. Full code can be found at github.com/layer6ai-labs/msc-sql.</abstract>
<identifier type="citekey">gorti-etal-2025-msc</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.107</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.107/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>2145</start>
<end>2160</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation
%A Gorti, Satya Krishna
%A Gofman, Ilan
%A Liu, Zhaoyan
%A Wu, Jiapeng
%A Vouitsis, Noël
%A Yu, Guangwei
%A Cresswell, Jesse C.
%A Hosseinzadeh, Rasa
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F gorti-etal-2025-msc
%X Text-to-SQL generation enables non-experts to interact with databases via natural language. Recent advances rely on large closed-source models like GPT-4 that present challenges in accessibility, privacy, and latency. To address these issues, we focus on developing small, efficient, and open-source text-to-SQL models. We demonstrate the benefits of sampling multiple candidate SQL generations and propose our method, MSc-SQL, to critique them using associated metadata. Our sample critiquing model evaluates multiple outputs simultaneously, achieving state-of-the-art performance compared to other open-source models while remaining competitive with larger models at a much lower cost. Full code can be found at github.com/layer6ai-labs/msc-sql.
%R 10.18653/v1/2025.naacl-long.107
%U https://aclanthology.org/2025.naacl-long.107/
%U https://doi.org/10.18653/v1/2025.naacl-long.107
%P 2145-2160
Markdown (Informal)
[MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation](https://aclanthology.org/2025.naacl-long.107/) (Gorti et al., NAACL 2025)
ACL
- Satya Krishna Gorti, Ilan Gofman, Zhaoyan Liu, Jiapeng Wu, Noël Vouitsis, Guangwei Yu, Jesse C. Cresswell, and Rasa Hosseinzadeh. 2025. MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 2145–2160, Albuquerque, New Mexico. Association for Computational Linguistics.