@inproceedings{sun-etal-2023-sqlprompt,
title = "{SQLP}rompt: In-Context Text-to-{SQL} with Minimal Labeled Data",
author = "Sun, Ruoxi and
Arik, Sercan and
Sinha, Rajarishi and
Nakhost, Hootan and
Dai, Hanjun and
Yin, Pengcheng and
Pfister, Tomas",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.39",
doi = "10.18653/v1/2023.findings-emnlp.39",
pages = "542--550",
abstract = "Text-to-SQL aims to automate the process of generating SQL queries on a database from natural language text. In this work, we propose {``}SQLPrompt{''}, tailored to improve the few-shot prompting capabilities of Text-to-SQL for Large Language Models (LLMs). Our methods include innovative prompt design, execution-based consistency decoding strategy which selects the SQL with the most consistent execution outcome among other SQL proposals, and a method that aims to improve performance by diversifying the SQL proposals during consistency selection with different prompt designs ({``}MixPrompt{''}) and foundation models ({``}MixLLMs{''}). We show that \textit{SQLPrompt} outperforms previous approaches for in-context learning with zero labeled data by a large margin, closing the gap with finetuning state-of-the-art with thousands of labeled data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2023-sqlprompt">
<titleInfo>
<title>SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruoxi</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sercan</namePart>
<namePart type="family">Arik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajarishi</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hootan</namePart>
<namePart type="family">Nakhost</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanjun</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengcheng</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomas</namePart>
<namePart type="family">Pfister</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text-to-SQL aims to automate the process of generating SQL queries on a database from natural language text. In this work, we propose “SQLPrompt”, tailored to improve the few-shot prompting capabilities of Text-to-SQL for Large Language Models (LLMs). Our methods include innovative prompt design, execution-based consistency decoding strategy which selects the SQL with the most consistent execution outcome among other SQL proposals, and a method that aims to improve performance by diversifying the SQL proposals during consistency selection with different prompt designs (“MixPrompt”) and foundation models (“MixLLMs”). We show that SQLPrompt outperforms previous approaches for in-context learning with zero labeled data by a large margin, closing the gap with finetuning state-of-the-art with thousands of labeled data.</abstract>
<identifier type="citekey">sun-etal-2023-sqlprompt</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.39</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.39</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>542</start>
<end>550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data
%A Sun, Ruoxi
%A Arik, Sercan
%A Sinha, Rajarishi
%A Nakhost, Hootan
%A Dai, Hanjun
%A Yin, Pengcheng
%A Pfister, Tomas
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F sun-etal-2023-sqlprompt
%X Text-to-SQL aims to automate the process of generating SQL queries on a database from natural language text. In this work, we propose “SQLPrompt”, tailored to improve the few-shot prompting capabilities of Text-to-SQL for Large Language Models (LLMs). Our methods include innovative prompt design, execution-based consistency decoding strategy which selects the SQL with the most consistent execution outcome among other SQL proposals, and a method that aims to improve performance by diversifying the SQL proposals during consistency selection with different prompt designs (“MixPrompt”) and foundation models (“MixLLMs”). We show that SQLPrompt outperforms previous approaches for in-context learning with zero labeled data by a large margin, closing the gap with finetuning state-of-the-art with thousands of labeled data.
%R 10.18653/v1/2023.findings-emnlp.39
%U https://aclanthology.org/2023.findings-emnlp.39
%U https://doi.org/10.18653/v1/2023.findings-emnlp.39
%P 542-550
Markdown (Informal)
[SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data](https://aclanthology.org/2023.findings-emnlp.39) (Sun et al., Findings 2023)
ACL
- Ruoxi Sun, Sercan Arik, Rajarishi Sinha, Hootan Nakhost, Hanjun Dai, Pengcheng Yin, and Tomas Pfister. 2023. SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 542–550, Singapore. Association for Computational Linguistics.