<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yadav-2026-tug">
    <titleInfo>
        <title>Tug-of-War Tuning: Capacity and Cross-Lingual Transfer in Zero-Shot NER</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tanushree</namePart>
        <namePart type="given">Ravindra</namePart>
        <namePart type="given">Pratap</namePart>
        <namePart type="family">Yadav</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 10th Widening NLP Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Chen</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Emily</namePart>
            <namePart type="family">Allaway</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Meryem</namePart>
            <namePart type="family">M’hamdi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Peerat</namePart>
            <namePart type="family">Limkonchotiwat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Richard</namePart>
            <namePart type="given">He</namePart>
            <namePart type="family">Bai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <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">Surendrabikram</namePart>
            <namePart type="family">Thapa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yinqiao</namePart>
            <namePart type="family">Li</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">979-8-89176-472-9</identifier>
    </relatedItem>
    <abstract>We investigate how the amount of fine-tuned capacity affects zero-shot cross-lingual transfer for named entity recognition (NER). Training exclusively on English WikiANN and evaluating on 14 typologically diverse target languages, we find a consistent inverted-U pattern: cross-lingual transfer is worst at both ends of the parameter-efficiency spectrum. Full fine-tuning, which updates all parameters, transfers worst overall and collapses on non-Latin-script languages, while the most parameter-efficient methods, (IA)³ and prefix tuning, also underperform. Methods with an intermediate number of trainable parameters (Low-Rank Adaptation, LoRA; Hu et al., 2022, and Houlsby adapters) transfer best, with LoRA outperforming full fine-tuning by roughly 7 F1 points on average and by over 10 points on languages such as Chinese and Japanese. We find the same inverted-U shape within LoRA alone: a sweep over ranks shows cross-lingual transfer peaking at an intermediate rank, distinct from the higher rank that maximises in-language English performance, revealing a rank–transfer tradeoff. We also examine, and do not find clean support for, the common assumption that better preservation of cross-lingual representational alignment explains PEFT’s transfer benefits: the method that best preserves a standard alignment measure transfers worst, while LoRA’s larger alignment shift coincides with its best transfer. Given known limitations of this alignment measure, we present this as a preliminary, metric-dependent observation that motivates further analysis with more robust alignment metrics, rather than a settled claim.</abstract>
    <identifier type="citekey">yadav-2026-tug</identifier>
    <location>
        <url>https://aclanthology.org/2026.winlp-main.1/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1</start>
            <end>9</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Tug-of-War Tuning: Capacity and Cross-Lingual Transfer in Zero-Shot NER
%A Yadav, Tanushree Ravindra Pratap
%Y Zhang, Chen
%Y Allaway, Emily
%Y M’hamdi, Meryem
%Y Limkonchotiwat, Peerat
%Y Bai, Richard He
%Y T.Y.S.S., Santosh
%Y Thapa, Surendrabikram
%Y Li, Yinqiao
%S Proceedings of the 10th Widening NLP Workshop
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-472-9
%F yadav-2026-tug
%X We investigate how the amount of fine-tuned capacity affects zero-shot cross-lingual transfer for named entity recognition (NER). Training exclusively on English WikiANN and evaluating on 14 typologically diverse target languages, we find a consistent inverted-U pattern: cross-lingual transfer is worst at both ends of the parameter-efficiency spectrum. Full fine-tuning, which updates all parameters, transfers worst overall and collapses on non-Latin-script languages, while the most parameter-efficient methods, (IA)³ and prefix tuning, also underperform. Methods with an intermediate number of trainable parameters (Low-Rank Adaptation, LoRA; Hu et al., 2022, and Houlsby adapters) transfer best, with LoRA outperforming full fine-tuning by roughly 7 F1 points on average and by over 10 points on languages such as Chinese and Japanese. We find the same inverted-U shape within LoRA alone: a sweep over ranks shows cross-lingual transfer peaking at an intermediate rank, distinct from the higher rank that maximises in-language English performance, revealing a rank–transfer tradeoff. We also examine, and do not find clean support for, the common assumption that better preservation of cross-lingual representational alignment explains PEFT’s transfer benefits: the method that best preserves a standard alignment measure transfers worst, while LoRA’s larger alignment shift coincides with its best transfer. Given known limitations of this alignment measure, we present this as a preliminary, metric-dependent observation that motivates further analysis with more robust alignment metrics, rather than a settled claim.
%U https://aclanthology.org/2026.winlp-main.1/
%P 1-9

Markdown (Informal)

[Tug-of-War Tuning: Capacity and Cross-Lingual Transfer in Zero-Shot NER](https://aclanthology.org/2026.winlp-main.1/) (Yadav, WiNLP 2026)

• Tug-of-War Tuning: Capacity and Cross-Lingual Transfer in Zero-Shot NER (Yadav, WiNLP 2026)

ACL

• Tanushree Ravindra Pratap Yadav. 2026. Tug-of-War Tuning: Capacity and Cross-Lingual Transfer in Zero-Shot NER. In Proceedings of the 10th Widening NLP Workshop, pages 1–9, Budapest, Hungary. Association for Computational Linguistics.