<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mondal-etal-2025-language">
    <titleInfo>
        <title>Language-Specific Neurons Do Not Facilitate Cross-Lingual Transfer</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Soumen</namePart>
        <namePart type="given">Kumar</namePart>
        <namePart type="family">Mondal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sayambhu</namePart>
        <namePart type="family">Sen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Abhishek</namePart>
        <namePart type="family">Singhania</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Preethi</namePart>
        <namePart type="family">Jyothi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>The Sixth Workshop on Insights from Negative Results in NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Aleksandr</namePart>
            <namePart type="family">Drozd</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">João</namePart>
            <namePart type="family">Sedoc</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shabnam</namePart>
            <namePart type="family">Tafreshi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Arjun</namePart>
            <namePart type="family">Akula</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Raphael</namePart>
            <namePart type="family">Shu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-240-4</identifier>
    </relatedItem>
    <abstract>Multilingual large language models (LLMs) aim towards robust natural language understanding across diverse languages, yet their performance significantly degrades on low-resource languages. This work explores whether existing techniques to identify language-specific neurons can be leveraged to enhance cross-lingual task performance of low-resource languages. We conduct detailed experiments covering existing language-specific neuron identification techniques (such as LanguageActivation Probability Entropy and activation probability-based thresholding) andneuron-specific LoRA fine-tuning with models like Llama 3.1 and Mistral Nemo. We find that such neuron-specific interventions are insufficient to yield cross-lingual improvements on downstream tasks (XNLI, XQuAD) in low-resource languages. This study highlights the challenges in achieving cross-lingual generalization and provides critical insights for multilingual LLMs.</abstract>
    <identifier type="citekey">mondal-etal-2025-language</identifier>
    <identifier type="doi">10.18653/v1/2025.insights-1.6</identifier>
    <location>
        <url>https://aclanthology.org/2025.insights-1.6/</url>
    </location>
    <part>
        <date>2025-05</date>
        <extent unit="page">
            <start>46</start>
            <end>62</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Language-Specific Neurons Do Not Facilitate Cross-Lingual Transfer
%A Mondal, Soumen Kumar
%A Sen, Sayambhu
%A Singhania, Abhishek
%A Jyothi, Preethi
%Y Drozd, Aleksandr
%Y Sedoc, João
%Y Tafreshi, Shabnam
%Y Akula, Arjun
%Y Shu, Raphael
%S The Sixth Workshop on Insights from Negative Results in NLP
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-240-4
%F mondal-etal-2025-language
%X Multilingual large language models (LLMs) aim towards robust natural language understanding across diverse languages, yet their performance significantly degrades on low-resource languages. This work explores whether existing techniques to identify language-specific neurons can be leveraged to enhance cross-lingual task performance of low-resource languages. We conduct detailed experiments covering existing language-specific neuron identification techniques (such as LanguageActivation Probability Entropy and activation probability-based thresholding) andneuron-specific LoRA fine-tuning with models like Llama 3.1 and Mistral Nemo. We find that such neuron-specific interventions are insufficient to yield cross-lingual improvements on downstream tasks (XNLI, XQuAD) in low-resource languages. This study highlights the challenges in achieving cross-lingual generalization and provides critical insights for multilingual LLMs.
%R 10.18653/v1/2025.insights-1.6
%U https://aclanthology.org/2025.insights-1.6/
%U https://doi.org/10.18653/v1/2025.insights-1.6
%P 46-62

Markdown (Informal)

[Language-Specific Neurons Do Not Facilitate Cross-Lingual Transfer](https://aclanthology.org/2025.insights-1.6/) (Mondal et al., insights 2025)

• Language-Specific Neurons Do Not Facilitate Cross-Lingual Transfer (Mondal et al., insights 2025)

ACL

• Soumen Kumar Mondal, Sayambhu Sen, Abhishek Singhania, and Preethi Jyothi. 2025. Language-Specific Neurons Do Not Facilitate Cross-Lingual Transfer. In The Sixth Workshop on Insights from Negative Results in NLP, pages 46–62, Albuquerque, New Mexico. Association for Computational Linguistics.