<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="accou-poelman-2026-tipa">
    <titleInfo>
        <title>TIPA: Typologically Informed Parameter Aggregation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Stef</namePart>
        <namePart type="family">Accou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wessel</namePart>
        <namePart type="family">Poelman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-386-9</identifier>
    </relatedItem>
    <abstract>Massively multilingual language models enable cross-lingual generalization but underperform on low-resource and unseen languages. While adapter-based fine-tuning offers a parameter-efficient solution, training language-specific adapters at scale remains costly. We introduce Typologically Informed Parameter Aggregation (TIPA), a training-free framework that constructs proxy language adapters by aggregating existing ones, weighted by typological similarity. Integrated into the MAD-X architecture, these proxies enable zero-shot cross-lingual transfer without additional training. We evaluate TIPA on five NLP tasks and over 230 languages. TIPA consistently outperforms baselines such as English-only fine-tuning and selecting the typologically closest-language adapter, with the largest gains for languages lacking dedicated adapters. Our results demonstrate that typologically informed aggregation provides a viable alternative to language-specific modules without any training needed.</abstract>
    <identifier type="citekey">accou-poelman-2026-tipa</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-eacl.119/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>2253</start>
            <end>2267</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TIPA: Typologically Informed Parameter Aggregation
%A Accou, Stef
%A Poelman, Wessel
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F accou-poelman-2026-tipa
%X Massively multilingual language models enable cross-lingual generalization but underperform on low-resource and unseen languages. While adapter-based fine-tuning offers a parameter-efficient solution, training language-specific adapters at scale remains costly. We introduce Typologically Informed Parameter Aggregation (TIPA), a training-free framework that constructs proxy language adapters by aggregating existing ones, weighted by typological similarity. Integrated into the MAD-X architecture, these proxies enable zero-shot cross-lingual transfer without additional training. We evaluate TIPA on five NLP tasks and over 230 languages. TIPA consistently outperforms baselines such as English-only fine-tuning and selecting the typologically closest-language adapter, with the largest gains for languages lacking dedicated adapters. Our results demonstrate that typologically informed aggregation provides a viable alternative to language-specific modules without any training needed.
%U https://aclanthology.org/2026.findings-eacl.119/
%P 2253-2267

Markdown (Informal)

[TIPA: Typologically Informed Parameter Aggregation](https://aclanthology.org/2026.findings-eacl.119/) (Accou & Poelman, Findings 2026)

• TIPA: Typologically Informed Parameter Aggregation (Accou & Poelman, Findings 2026)

ACL

• Stef Accou and Wessel Poelman. 2026. TIPA: Typologically Informed Parameter Aggregation. In Findings of the Association for Computational Linguistics: EACL 2026, pages 2253–2267, Rabat, Morocco. Association for Computational Linguistics.