<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2025-mitigating">
    <titleInfo>
        <title>Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kangda</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hasnat</namePart>
        <namePart type="given">Md</namePart>
        <namePart type="family">Abdullah</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruihong</namePart>
        <namePart type="family">Huang</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>Large Language Models (LLMs) often exhibit gender bias, resulting in unequal treatment of male and female subjects across different contexts. To address this issue, we propose a novel data generation framework that fosters exploratory thinking in LLMs. Our approach prompts models to generate story pairs featuring male and female protagonists in structurally identical, morally ambiguous scenarios, then elicits and compares their moral judgments. When inconsistencies arise, the model is guided to produce balanced, gender-neutral judgments. These story-judgment pairs are used to fine-tune or optimize the models via Direct Preference Optimization (DPO). Experimental results show that our method significantly reduces gender bias while preserving or even enhancing general model capabilities. We will release the code and generated data.</abstract>
    <identifier type="citekey">wei-etal-2025-mitigating</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.364/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>6895</start>
            <end>6917</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs
%A Wei, Kangda
%A Abdullah, Hasnat Md
%A Huang, Ruihong
%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 wei-etal-2025-mitigating
%X Large Language Models (LLMs) often exhibit gender bias, resulting in unequal treatment of male and female subjects across different contexts. To address this issue, we propose a novel data generation framework that fosters exploratory thinking in LLMs. Our approach prompts models to generate story pairs featuring male and female protagonists in structurally identical, morally ambiguous scenarios, then elicits and compares their moral judgments. When inconsistencies arise, the model is guided to produce balanced, gender-neutral judgments. These story-judgment pairs are used to fine-tune or optimize the models via Direct Preference Optimization (DPO). Experimental results show that our method significantly reduces gender bias while preserving or even enhancing general model capabilities. We will release the code and generated data.
%U https://aclanthology.org/2025.findings-emnlp.364/
%P 6895-6917

Markdown (Informal)

[Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs](https://aclanthology.org/2025.findings-emnlp.364/) (Wei et al., Findings 2025)

• Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs (Wei et al., Findings 2025)

ACL

• Kangda Wei, Hasnat Md Abdullah, and Ruihong Huang. 2025. Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 6895–6917, Suzhou, China. Association for Computational Linguistics.