<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poterti-etal-2025-role">
    <titleInfo>
        <title>Can Role Vectors Affect LLM Behaviour?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Daniele</namePart>
        <namePart type="family">Potertì</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrea</namePart>
        <namePart type="family">Seveso</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fabio</namePart>
        <namePart type="family">Mercorio</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 influence of personas on Large Language Models (LLMs) has been widely studied, yet their direct impact on performance remains uncertain. This work explores a novel approach to guiding LLM behaviour through role vectors, an alternative to persona-based prompting. We construct 29 role vectors derived from model activations and evaluate their impact on benchmark performance across multiple domains. Our analysis investigates whether these vectors can effectively steer models toward domain-specific expertise. We measure two key interventions: (i) activation addition, which reinforces role-specific directions, and (ii) directional ablation, which removes them. Results on well-established benchmarks indicate that role vectors do, in fact, influence model behaviour, improving in-domain task performance while also yielding unexpected cross-domain gains.This, in turn, suggests that manipulating internal model representations has a greater impact on outcomes than persona-based prompting.</abstract>
    <identifier type="citekey">poterti-etal-2025-role</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.963/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>17735</start>
            <end>17747</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Can Role Vectors Affect LLM Behaviour?
%A Potertì, Daniele
%A Seveso, Andrea
%A Mercorio, Fabio
%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 poterti-etal-2025-role
%X The influence of personas on Large Language Models (LLMs) has been widely studied, yet their direct impact on performance remains uncertain. This work explores a novel approach to guiding LLM behaviour through role vectors, an alternative to persona-based prompting. We construct 29 role vectors derived from model activations and evaluate their impact on benchmark performance across multiple domains. Our analysis investigates whether these vectors can effectively steer models toward domain-specific expertise. We measure two key interventions: (i) activation addition, which reinforces role-specific directions, and (ii) directional ablation, which removes them. Results on well-established benchmarks indicate that role vectors do, in fact, influence model behaviour, improving in-domain task performance while also yielding unexpected cross-domain gains.This, in turn, suggests that manipulating internal model representations has a greater impact on outcomes than persona-based prompting.
%U https://aclanthology.org/2025.findings-emnlp.963/
%P 17735-17747

Markdown (Informal)

[Can Role Vectors Affect LLM Behaviour?](https://aclanthology.org/2025.findings-emnlp.963/) (Potertì et al., Findings 2025)

• Can Role Vectors Affect LLM Behaviour? (Potertì et al., Findings 2025)

ACL

• Daniele Potertì, Andrea Seveso, and Fabio Mercorio. 2025. Can Role Vectors Affect LLM Behaviour?. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 17735–17747, Suzhou, China. Association for Computational Linguistics.