@inproceedings{zhao-etal-2024-minorities,
title = "More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation",
author = "Zhao, Jiaxu and
Shi, Zijing and
Li, Yitong and
Pei, Yulong and
Chen, Ling and
Fang, Meng and
Pechenizkiy, Mykola",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.594",
pages = "9987--10001",
abstract = "Pretrained models learned from real corpora can often capture undesirable features, leading to bias issues against different demographic groups. Most existing studies on bias dataset construction or bias mitigation methods only focus on one demographic group pair to study a certain bias, e.g. \textit{black} vs. \textit{white} for racial bias. However, in real-world applications, there are more than two demographic groups that are at risk of the same bias. In this paper, we propose to analyze and reduce biases across multiple demographic groups. We collect and build a multi-demographic bias dataset including five commonly discussed bias dimensions. To mitigate multi-demographic bias, we adopt several novel debiasing methods, including regularisation-based and augmentation-based methods, as well as appropriate evaluation metrics for multi-demographic bias measurement. Experimental results on the proposed multi-demographic dataset show that a fairer model can be achieved using a multi-demographic debiasing approach. Also, the model debiased using the proposed multi-demographic debiasing methods can better transfer to unseen demographics without sacrificing the performance of the pretrained model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2024-minorities">
<titleInfo>
<title>More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaxu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zijing</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yitong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulong</namePart>
<namePart type="family">Pei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ling</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mykola</namePart>
<namePart type="family">Pechenizkiy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pretrained models learned from real corpora can often capture undesirable features, leading to bias issues against different demographic groups. Most existing studies on bias dataset construction or bias mitigation methods only focus on one demographic group pair to study a certain bias, e.g. black vs. white for racial bias. However, in real-world applications, there are more than two demographic groups that are at risk of the same bias. In this paper, we propose to analyze and reduce biases across multiple demographic groups. We collect and build a multi-demographic bias dataset including five commonly discussed bias dimensions. To mitigate multi-demographic bias, we adopt several novel debiasing methods, including regularisation-based and augmentation-based methods, as well as appropriate evaluation metrics for multi-demographic bias measurement. Experimental results on the proposed multi-demographic dataset show that a fairer model can be achieved using a multi-demographic debiasing approach. Also, the model debiased using the proposed multi-demographic debiasing methods can better transfer to unseen demographics without sacrificing the performance of the pretrained model.</abstract>
<identifier type="citekey">zhao-etal-2024-minorities</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.594</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>9987</start>
<end>10001</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation
%A Zhao, Jiaxu
%A Shi, Zijing
%A Li, Yitong
%A Pei, Yulong
%A Chen, Ling
%A Fang, Meng
%A Pechenizkiy, Mykola
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F zhao-etal-2024-minorities
%X Pretrained models learned from real corpora can often capture undesirable features, leading to bias issues against different demographic groups. Most existing studies on bias dataset construction or bias mitigation methods only focus on one demographic group pair to study a certain bias, e.g. black vs. white for racial bias. However, in real-world applications, there are more than two demographic groups that are at risk of the same bias. In this paper, we propose to analyze and reduce biases across multiple demographic groups. We collect and build a multi-demographic bias dataset including five commonly discussed bias dimensions. To mitigate multi-demographic bias, we adopt several novel debiasing methods, including regularisation-based and augmentation-based methods, as well as appropriate evaluation metrics for multi-demographic bias measurement. Experimental results on the proposed multi-demographic dataset show that a fairer model can be achieved using a multi-demographic debiasing approach. Also, the model debiased using the proposed multi-demographic debiasing methods can better transfer to unseen demographics without sacrificing the performance of the pretrained model.
%U https://aclanthology.org/2024.findings-acl.594
%P 9987-10001
Markdown (Informal)
[More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation](https://aclanthology.org/2024.findings-acl.594) (Zhao et al., Findings 2024)
ACL