<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barker-kazakov-2025-mitigating">
    <titleInfo>
        <title>Mitigating Bias in Text Classification via Prompt-Based Text Transformation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Charmaine</namePart>
        <namePart type="family">Barker</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dimitar</namePart>
        <namePart type="family">Kazakov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Kunilovskaya</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marie</namePart>
            <namePart type="family">Escribe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The presence of specific linguistic signals particular to a certain sub-group can become highly salient to language models during training. In automated decision-making settings, this may lead to biased outcomes when models rely on cues that correlate with protected characteristics. We investigate whether prompting ChatGPT to rewrite text using simplification, neutralisation, localisation, and formalisation can reduce demographic signals while preserving meaning. Experimental results show a statistically significant drop in location classification accuracy across multiple models after transformation, suggesting reduced reliance on group-specific language. At the same time, sentiment analysis and rating prediction tasks confirm that the core meaning of the reviews remains greatly intact. These results suggest that prompt-based rewriting offers a practical and generalisable approach for mitigating bias in text classification.</abstract>
    <identifier type="citekey">barker-kazakov-2025-mitigating</identifier>
    <location>
        <url>https://aclanthology.org/2025.ranlp-1.17/</url>
    </location>
    <part>
        <date>2025-09</date>
        <extent unit="page">
            <start>143</start>
            <end>149</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Mitigating Bias in Text Classification via Prompt-Based Text Transformation
%A Barker, Charmaine
%A Kazakov, Dimitar
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F barker-kazakov-2025-mitigating
%X The presence of specific linguistic signals particular to a certain sub-group can become highly salient to language models during training. In automated decision-making settings, this may lead to biased outcomes when models rely on cues that correlate with protected characteristics. We investigate whether prompting ChatGPT to rewrite text using simplification, neutralisation, localisation, and formalisation can reduce demographic signals while preserving meaning. Experimental results show a statistically significant drop in location classification accuracy across multiple models after transformation, suggesting reduced reliance on group-specific language. At the same time, sentiment analysis and rating prediction tasks confirm that the core meaning of the reviews remains greatly intact. These results suggest that prompt-based rewriting offers a practical and generalisable approach for mitigating bias in text classification.
%U https://aclanthology.org/2025.ranlp-1.17/
%P 143-149

Markdown (Informal)

[Mitigating Bias in Text Classification via Prompt-Based Text Transformation](https://aclanthology.org/2025.ranlp-1.17/) (Barker & Kazakov, RANLP 2025)

• Mitigating Bias in Text Classification via Prompt-Based Text Transformation (Barker & Kazakov, RANLP 2025)

ACL

• Charmaine Barker and Dimitar Kazakov. 2025. Mitigating Bias in Text Classification via Prompt-Based Text Transformation. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 143–149, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.