@inproceedings{bi-etal-2025-group,
title = "A Group Fairness Lens for Large Language Models",
author = "Bi, Guanqun and
Xie, Yuqiang and
Shen, Lei and
Cao, Yanan",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.431/",
pages = "8117--8139",
ISBN = "979-8-89176-335-7",
abstract = "The rapid advancement of large language models has revolutionized various applications but also raised crucial concerns about their potential to perpetuate biases and unfairness when deployed in social media contexts. Evaluating LLMs' potential biases and fairness has become crucial, as existing methods rely on limited prompts focusing on just a few groups, lacking a comprehensive categorical perspective. In this paper, we propose evaluating LLM biases from a group fairness lens using a novel hierarchical schema characterizing diverse social groups. Specifically, we construct a dataset, GFair, encapsulating target-attribute combinations across multiple dimensions. In addition, we introduce statement organization, a new open-ended text generation task, to uncover complex biases in LLMs. Extensive evaluations of popular LLMs reveal inherent safety concerns. To mitigate the biases of LLM from a group fairness perspective, we pioneer a novel chain-of-thought method GF-Think to mitigate biases of LLMs from a group fairness perspective. Experimental results demonstrate its efficacy in mitigating bias in LLMs to achieve fairness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bi-etal-2025-group">
<titleInfo>
<title>A Group Fairness Lens for Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guanqun</namePart>
<namePart type="family">Bi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuqiang</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanan</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>The rapid advancement of large language models has revolutionized various applications but also raised crucial concerns about their potential to perpetuate biases and unfairness when deployed in social media contexts. Evaluating LLMs’ potential biases and fairness has become crucial, as existing methods rely on limited prompts focusing on just a few groups, lacking a comprehensive categorical perspective. In this paper, we propose evaluating LLM biases from a group fairness lens using a novel hierarchical schema characterizing diverse social groups. Specifically, we construct a dataset, GFair, encapsulating target-attribute combinations across multiple dimensions. In addition, we introduce statement organization, a new open-ended text generation task, to uncover complex biases in LLMs. Extensive evaluations of popular LLMs reveal inherent safety concerns. To mitigate the biases of LLM from a group fairness perspective, we pioneer a novel chain-of-thought method GF-Think to mitigate biases of LLMs from a group fairness perspective. Experimental results demonstrate its efficacy in mitigating bias in LLMs to achieve fairness.</abstract>
<identifier type="citekey">bi-etal-2025-group</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.431/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>8117</start>
<end>8139</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Group Fairness Lens for Large Language Models
%A Bi, Guanqun
%A Xie, Yuqiang
%A Shen, Lei
%A Cao, Yanan
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F bi-etal-2025-group
%X The rapid advancement of large language models has revolutionized various applications but also raised crucial concerns about their potential to perpetuate biases and unfairness when deployed in social media contexts. Evaluating LLMs’ potential biases and fairness has become crucial, as existing methods rely on limited prompts focusing on just a few groups, lacking a comprehensive categorical perspective. In this paper, we propose evaluating LLM biases from a group fairness lens using a novel hierarchical schema characterizing diverse social groups. Specifically, we construct a dataset, GFair, encapsulating target-attribute combinations across multiple dimensions. In addition, we introduce statement organization, a new open-ended text generation task, to uncover complex biases in LLMs. Extensive evaluations of popular LLMs reveal inherent safety concerns. To mitigate the biases of LLM from a group fairness perspective, we pioneer a novel chain-of-thought method GF-Think to mitigate biases of LLMs from a group fairness perspective. Experimental results demonstrate its efficacy in mitigating bias in LLMs to achieve fairness.
%U https://aclanthology.org/2025.findings-emnlp.431/
%P 8117-8139
Markdown (Informal)
[A Group Fairness Lens for Large Language Models](https://aclanthology.org/2025.findings-emnlp.431/) (Bi et al., Findings 2025)
ACL
- Guanqun Bi, Yuqiang Xie, Lei Shen, and Yanan Cao. 2025. A Group Fairness Lens for Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 8117–8139, Suzhou, China. Association for Computational Linguistics.