@inproceedings{wang-etal-2024-improving-demonstration,
title = "Improving Demonstration Diversity by Human-Free Fusing for Text-to-{SQL}",
author = "Wang, Dingzirui and
Dou, Longxu and
Zhang, Xuanliang and
Zhu, Qingfu and
Che, Wanxiang",
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.65",
pages = "1193--1207",
abstract = "In-context learning with large language models (LLMs) is the current mainstream method for text-to-SQL. Previous studies have explored selecting relevant demonstrations from a human-labeled demonstration pool, but these methods lack diversity and incur high labeling costs. In this work, we address measuring and enhancing the diversity of the text-to-SQL demonstration pool. First, we introduce a diversity metric and present that the diversity of the existing labeling data can be further enhanced. Motivated by these findings, we propose Fused that iteratively fuses demonstrations to create a diverse demonstration pool based on human labeling or even from scratch with LLMs, reducing labeling costs. Fused achieves an average improvement of 2.1{\%} based on existing labeling and 5.5{\%} from scratch on several mainstream datasets, demonstrating its effectiveness.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-improving-demonstration">
<titleInfo>
<title>Improving Demonstration Diversity by Human-Free Fusing for Text-to-SQL</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dingzirui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longxu</namePart>
<namePart type="family">Dou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanliang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingfu</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</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>In-context learning with large language models (LLMs) is the current mainstream method for text-to-SQL. Previous studies have explored selecting relevant demonstrations from a human-labeled demonstration pool, but these methods lack diversity and incur high labeling costs. In this work, we address measuring and enhancing the diversity of the text-to-SQL demonstration pool. First, we introduce a diversity metric and present that the diversity of the existing labeling data can be further enhanced. Motivated by these findings, we propose Fused that iteratively fuses demonstrations to create a diverse demonstration pool based on human labeling or even from scratch with LLMs, reducing labeling costs. Fused achieves an average improvement of 2.1% based on existing labeling and 5.5% from scratch on several mainstream datasets, demonstrating its effectiveness.</abstract>
<identifier type="citekey">wang-etal-2024-improving-demonstration</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.65</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>1193</start>
<end>1207</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Demonstration Diversity by Human-Free Fusing for Text-to-SQL
%A Wang, Dingzirui
%A Dou, Longxu
%A Zhang, Xuanliang
%A Zhu, Qingfu
%A Che, Wanxiang
%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 wang-etal-2024-improving-demonstration
%X In-context learning with large language models (LLMs) is the current mainstream method for text-to-SQL. Previous studies have explored selecting relevant demonstrations from a human-labeled demonstration pool, but these methods lack diversity and incur high labeling costs. In this work, we address measuring and enhancing the diversity of the text-to-SQL demonstration pool. First, we introduce a diversity metric and present that the diversity of the existing labeling data can be further enhanced. Motivated by these findings, we propose Fused that iteratively fuses demonstrations to create a diverse demonstration pool based on human labeling or even from scratch with LLMs, reducing labeling costs. Fused achieves an average improvement of 2.1% based on existing labeling and 5.5% from scratch on several mainstream datasets, demonstrating its effectiveness.
%U https://aclanthology.org/2024.findings-emnlp.65
%P 1193-1207
Markdown (Informal)
[Improving Demonstration Diversity by Human-Free Fusing for Text-to-SQL](https://aclanthology.org/2024.findings-emnlp.65) (Wang et al., Findings 2024)
ACL