<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2026-pararater">
    <titleInfo>
        <title>ParaRater: Enhancing Cross-Lingual Transfer in LLMs with Meta-Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wenhan</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Binbin</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhixun</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yifan</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mykola</namePart>
        <namePart type="family">Pechenizkiy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Meng</namePart>
        <namePart type="family">Fang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yin</namePart>
        <namePart type="family">Zheng</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Multilingual LLMs increasingly claim broad language coverage, yet their performance still lags far behind English in many languages. Because low resource data is scarce and noisy, improving these languages directly is difficult, making cross lingual transfer from English a natural alternative. Parallel corpora are central to such transfer, but it remains unclear which kinds of parallel data matter most. We propose ParaRater, a corpus selection method that identifies high value English text to translate into target languages, building parallel corpora that most efficiently improve target language performance. ParaRater uses meta learning to tie selection directly to downstream accuracy on native target language data, and applies a two stage filter to find samples that only help when both language versions are used in training, capturing truly impactful parallel data. Experiments across Chinese, German, French, Japanese, Thai, Arabic, Tagalog, and Russian, together with qualitative analyses, support these findings.</abstract>
    <identifier type="citekey">han-etal-2026-pararater</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1760/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>40131</start>
            <end>40144</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ParaRater: Enhancing Cross-Lingual Transfer in LLMs with Meta-Learning
%A Han, Wenhan
%A Liu, Binbin
%A Chen, Zhixun
%A Zhang, Yifan
%A Pechenizkiy, Mykola
%A Fang, Meng
%A Zheng, Yin
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F han-etal-2026-pararater
%X Multilingual LLMs increasingly claim broad language coverage, yet their performance still lags far behind English in many languages. Because low resource data is scarce and noisy, improving these languages directly is difficult, making cross lingual transfer from English a natural alternative. Parallel corpora are central to such transfer, but it remains unclear which kinds of parallel data matter most. We propose ParaRater, a corpus selection method that identifies high value English text to translate into target languages, building parallel corpora that most efficiently improve target language performance. ParaRater uses meta learning to tie selection directly to downstream accuracy on native target language data, and applies a two stage filter to find samples that only help when both language versions are used in training, capturing truly impactful parallel data. Experiments across Chinese, German, French, Japanese, Thai, Arabic, Tagalog, and Russian, together with qualitative analyses, support these findings.
%U https://aclanthology.org/2026.emnlp-main.1760/
%P 40131-40144

Markdown (Informal)

[ParaRater: Enhancing Cross-Lingual Transfer in LLMs with Meta-Learning](https://aclanthology.org/2026.emnlp-main.1760/) (Han et al., EMNLP 2026)

• ParaRater: Enhancing Cross-Lingual Transfer in LLMs with Meta-Learning (Han et al., EMNLP 2026)

ACL

• Wenhan Han, Binbin Liu, Zhixun Chen, Yifan Zhang, Mykola Pechenizkiy, Meng Fang, and Yin Zheng. 2026. ParaRater: Enhancing Cross-Lingual Transfer in LLMs with Meta-Learning. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 40131–40144, Budapest, Hungary. Association for Computational Linguistics.