<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nadeem-etal-2025-steering">
    <titleInfo>
        <title>Steering Towards Fairness: Mitigating Political Stance Bias in LLMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Afrozah</namePart>
        <namePart type="family">Nadeem</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mark</namePart>
        <namePart type="family">Dras</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Usman</namePart>
        <namePart type="family">Naseem</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 8th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Texts</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ali</namePart>
            <namePart type="family">Hürriyetoğlu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hristo</namePart>
            <namePart type="family">Tanev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Surendrabikram</namePart>
            <namePart type="family">Thapa</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>Recent advancements in large language models (LLMs) have enabled their widespread use across diverse real-world applications. However, concerns remain about their tendency to encode and reproduce ideological biases along political and economic dimensions. In this paper, we employ a framework for probing and mitigating such biases in decoder-based LLMs through analysis of internal model representations. Grounded in the Political Compass Test (PCT), this method uses contrastive pairs to extract and compare hidden layer activations from models like Mistral and DeepSeek. We introduce a comprehensive activation extraction pipeline capable of layer-wise analysis across multiple ideological axes, revealing meaningful disparities linked to political framing. Our results show that decoder LLMs systematically encode representational bias across layers, which can be leveraged for effective steering vector-based mitigation. This work provides new insights into how political bias is encoded in LLMs and offers a principled approach to debiasing beyond surface-level output interventions.</abstract>
    <identifier type="citekey">nadeem-etal-2025-steering</identifier>
    <location>
        <url>https://aclanthology.org/2025.case-1.6/</url>
    </location>
    <part>
        <date>2025-09</date>
        <extent unit="page">
            <start>52</start>
            <end>61</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Steering Towards Fairness: Mitigating Political Stance Bias in LLMs
%A Nadeem, Afrozah
%A Dras, Mark
%A Naseem, Usman
%Y Hürriyetoğlu, Ali
%Y Tanev, Hristo
%Y Thapa, Surendrabikram
%S Proceedings of the 8th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Texts
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F nadeem-etal-2025-steering
%X Recent advancements in large language models (LLMs) have enabled their widespread use across diverse real-world applications. However, concerns remain about their tendency to encode and reproduce ideological biases along political and economic dimensions. In this paper, we employ a framework for probing and mitigating such biases in decoder-based LLMs through analysis of internal model representations. Grounded in the Political Compass Test (PCT), this method uses contrastive pairs to extract and compare hidden layer activations from models like Mistral and DeepSeek. We introduce a comprehensive activation extraction pipeline capable of layer-wise analysis across multiple ideological axes, revealing meaningful disparities linked to political framing. Our results show that decoder LLMs systematically encode representational bias across layers, which can be leveraged for effective steering vector-based mitigation. This work provides new insights into how political bias is encoded in LLMs and offers a principled approach to debiasing beyond surface-level output interventions.
%U https://aclanthology.org/2025.case-1.6/
%P 52-61

Markdown (Informal)

[Steering Towards Fairness: Mitigating Political Stance Bias in LLMs](https://aclanthology.org/2025.case-1.6/) (Nadeem et al., CASE 2025)

• Steering Towards Fairness: Mitigating Political Stance Bias in LLMs (Nadeem et al., CASE 2025)

ACL

• Afrozah Nadeem, Mark Dras, and Usman Naseem. 2025. Steering Towards Fairness: Mitigating Political Stance Bias in LLMs. In Proceedings of the 8th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Texts, pages 52–61, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.