<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-minku-2026-cross">
    <titleInfo>
        <title>Cross-Lingual Transfer of Evil Vectors Is Directionally Asymmetric</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Juann</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kang</namePart>
        <namePart type="family">MinKu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="given">Ifeoluwa</namePart>
            <namePart type="family">Adelani</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jesujoba</namePart>
            <namePart type="family">Alabi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Catherine</namePart>
            <namePart type="family">Arnett</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tyler</namePart>
            <namePart type="family">Chang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">C</namePart>
            <namePart type="given">M</namePart>
            <namePart type="family">Downey</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Omer</namePart>
            <namePart type="family">Goldman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Senyu</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lester</namePart>
            <namePart type="given">James</namePart>
            <namePart type="given">Validad</namePart>
            <namePart type="family">Miranda</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jirui</namePart>
            <namePart type="family">Qi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Stap</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Genta</namePart>
            <namePart type="given">Indra</namePart>
            <namePart type="family">Winata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xinyu</namePart>
            <namePart type="given">Crystina</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-469-9</identifier>
    </relatedItem>
    <abstract>Persona vectors are linear directions in the residual-stream activations of LLMs that encode behavioral traits and enable fine-grained control over model behavior. Among them, the evil persona vector is particularly relevant to understanding harmful behavior, jailbreak vulnerabilities, and the unlearning of harmful knowledge. Yet whether this vector reflects a genuinely cross-lingual concept, rather than an artifact of its extraction language, remains untested. We conduct a systematic evil-vector transfer study across two high-resource languages (English, Spanish) and two low-resource languages (Swahili, Telugu) on four open-source instruction-tuned LLMs, and find that transfer is directionally asymmetric. Evil vectors are harder to obtain reliably from low-resource languages, and the resulting vectors are largely ineffective at steering, even within their own language. In contrast, vectors extracted from high-resource languages transfer effectively to low-resource inputs while largely preserving general knowledge, as measured by MMLU. Geometric analysis further supports this pattern: evil vectors from the two high-resource languages are closely aligned, whereas low-resource vectors align only weakly with this shared direction. These results suggest that a shared cross-lingual evil direction exists and, once reliably extracted from a high-resource language, can be reused to steer behavior in low-resource languages without additional per-language data collection.</abstract>
    <identifier type="citekey">kim-minku-2026-cross</identifier>
    <location>
        <url>https://aclanthology.org/2026.mrl-1.35/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>445</start>
            <end>454</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cross-Lingual Transfer of Evil Vectors Is Directionally Asymmetric
%A Kim, Juann
%A MinKu, Kang
%Y Adelani, David Ifeoluwa
%Y Alabi, Jesujoba
%Y Arnett, Catherine
%Y Chang, Tyler
%Y Downey, C. M.
%Y Goldman, Omer
%Y Li, Senyu
%Y Miranda, Lester James Validad
%Y Qi, Jirui
%Y Stap, David
%Y Winata, Genta Indra
%Y Zhang, Xinyu Crystina
%S Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-469-9
%F kim-minku-2026-cross
%X Persona vectors are linear directions in the residual-stream activations of LLMs that encode behavioral traits and enable fine-grained control over model behavior. Among them, the evil persona vector is particularly relevant to understanding harmful behavior, jailbreak vulnerabilities, and the unlearning of harmful knowledge. Yet whether this vector reflects a genuinely cross-lingual concept, rather than an artifact of its extraction language, remains untested. We conduct a systematic evil-vector transfer study across two high-resource languages (English, Spanish) and two low-resource languages (Swahili, Telugu) on four open-source instruction-tuned LLMs, and find that transfer is directionally asymmetric. Evil vectors are harder to obtain reliably from low-resource languages, and the resulting vectors are largely ineffective at steering, even within their own language. In contrast, vectors extracted from high-resource languages transfer effectively to low-resource inputs while largely preserving general knowledge, as measured by MMLU. Geometric analysis further supports this pattern: evil vectors from the two high-resource languages are closely aligned, whereas low-resource vectors align only weakly with this shared direction. These results suggest that a shared cross-lingual evil direction exists and, once reliably extracted from a high-resource language, can be reused to steer behavior in low-resource languages without additional per-language data collection.
%U https://aclanthology.org/2026.mrl-1.35/
%P 445-454

Markdown (Informal)

[Cross-Lingual Transfer of Evil Vectors Is Directionally Asymmetric](https://aclanthology.org/2026.mrl-1.35/) (Kim & MinKu, MRL 2026)

• Cross-Lingual Transfer of Evil Vectors Is Directionally Asymmetric (Kim & MinKu, MRL 2026)

ACL

• Juann Kim and Kang MinKu. 2026. Cross-Lingual Transfer of Evil Vectors Is Directionally Asymmetric. In Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026), pages 445–454, Budapest, Hungary. Association for Computational Linguistics.