<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cyberey-etal-2025-unsupervised">
    <titleInfo>
        <title>Unsupervised Concept Vector Extraction for Bias Control in LLMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hannah</namePart>
        <namePart type="family">Cyberey</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yangfeng</namePart>
        <namePart type="family">Ji</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Evans</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>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-332-6</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) are known to perpetuate stereotypes and exhibit biases. Various strategies have been proposed to mitigate these biases, but most work studies biases as a black-box problem without considering how concepts are represented within the model. We adapt techniques from representation engineering to study how the concept of “gender” is represented within LLMs. We introduce a new method that extracts concept representations via probability weighting without labeled data and efficiently selects a steering vector for measuring and manipulating the model’s representation. We develop a projection-based method that enables precise steering of model predictions and demonstrate its effectiveness in mitigating gender bias in LLMs and show that it also generalizes to racial bias.</abstract>
    <identifier type="citekey">cyberey-etal-2025-unsupervised</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.1439/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>28321</start>
            <end>28343</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Unsupervised Concept Vector Extraction for Bias Control in LLMs
%A Cyberey, Hannah
%A Ji, Yangfeng
%A Evans, David
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F cyberey-etal-2025-unsupervised
%X Large language models (LLMs) are known to perpetuate stereotypes and exhibit biases. Various strategies have been proposed to mitigate these biases, but most work studies biases as a black-box problem without considering how concepts are represented within the model. We adapt techniques from representation engineering to study how the concept of “gender” is represented within LLMs. We introduce a new method that extracts concept representations via probability weighting without labeled data and efficiently selects a steering vector for measuring and manipulating the model’s representation. We develop a projection-based method that enables precise steering of model predictions and demonstrate its effectiveness in mitigating gender bias in LLMs and show that it also generalizes to racial bias.
%U https://aclanthology.org/2025.emnlp-main.1439/
%P 28321-28343

Markdown (Informal)

[Unsupervised Concept Vector Extraction for Bias Control in LLMs](https://aclanthology.org/2025.emnlp-main.1439/) (Cyberey et al., EMNLP 2025)

• Unsupervised Concept Vector Extraction for Bias Control in LLMs (Cyberey et al., EMNLP 2025)

ACL

• Hannah Cyberey, Yangfeng Ji, and David Evans. 2025. Unsupervised Concept Vector Extraction for Bias Control in LLMs. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 28321–28343, Suzhou, China. Association for Computational Linguistics.