<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmed-etal-2026-disentangling">
    <titleInfo>
        <title>Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ahmed</namePart>
        <namePart type="given">Haj</namePart>
        <namePart type="family">Ahmed</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruochen</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alvin</namePart>
        <namePart type="given">C</namePart>
        <namePart type="family">Grissom II</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Santosh</namePart>
            <namePart type="family">T.Y.S.S.</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="given">Diego</namePart>
            <namePart type="family">Rodriguez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ona</namePart>
            <namePart type="family">de Gibert</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-393-7</identifier>
    </relatedItem>
    <abstract>We study cross-lingual transfer by fine-tuning seven large language models (4B–671B parameters) on Arabic and evaluating zero-shot reading comprehension on Semitic languages and non-Semitic controls. Across dense and Mixture-of-Experts architectures, we find no evidence of Semitic-specific transfer: models with weak baselines improve dramatically across all languages, while strong-baseline models show only marginal gains regardless of language family. A chain-of-thought ablation reinforces this finding: the same models that benefit most from fine-tuning benefit equally from inference-time reasoning, suggesting both mechanisms address task-format alignment rather than cross-lingual knowledge transfer.</abstract>
    <identifier type="citekey">ahmed-etal-2026-disentangling</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-srw.62/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>683</start>
            <end>700</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer
%A Ahmed, Ahmed Haj
%A Zhang, Ruochen
%A Grissom II, Alvin C.
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F ahmed-etal-2026-disentangling
%X We study cross-lingual transfer by fine-tuning seven large language models (4B–671B parameters) on Arabic and evaluating zero-shot reading comprehension on Semitic languages and non-Semitic controls. Across dense and Mixture-of-Experts architectures, we find no evidence of Semitic-specific transfer: models with weak baselines improve dramatically across all languages, while strong-baseline models show only marginal gains regardless of language family. A chain-of-thought ablation reinforces this finding: the same models that benefit most from fine-tuning benefit equally from inference-time reasoning, suggesting both mechanisms address task-format alignment rather than cross-lingual knowledge transfer.
%U https://aclanthology.org/2026.acl-srw.62/
%P 683-700

Markdown (Informal)

[Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer](https://aclanthology.org/2026.acl-srw.62/) (Ahmed et al., ACL 2026)

• Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer (Ahmed et al., ACL 2026)

ACL

• Ahmed Haj Ahmed, Ruochen Zhang, and Alvin C Grissom II. 2026. Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 683–700, San Diego, California, United States. Association for Computational Linguistics.