<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2025-crossin">
    <titleInfo>
        <title>CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Geyu</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bin</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhengyuan</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nancy</namePart>
        <namePart type="given">F</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-01</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second Workshop on Scaling Up Multilingual &amp; Multi-Cultural Evaluation</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those that are linguistically distant from English. This performance discrepancy mainly stems from the imbalanced distribution of training data across languages during pre-training and instruction tuning stages. To address this problem, we propose a novel approach called CrossIn, which utilizes a mixed composition of cross-lingual instruction tuning data. Our method leverages the compressed representation shared by various languages to efficiently enhance the model‘s task-solving capabilities and multilingual proficiency within a single process. In addition, we introduce a multi-task and multi-faceted benchmark to evaluate the effectiveness of CrossIn. Experimental results demonstrate that our method substantially improves performance across tasks and languages, and we provide extensive insights into the impact of cross-lingual data volume and the integration of translation data on enhancing multilingual consistency and accuracy.</abstract>
    <identifier type="citekey">lin-etal-2025-crossin</identifier>
    <location>
        <url>https://aclanthology.org/2025.sumeval-2.2/</url>
    </location>
    <part>
        <date>2025-01</date>
        <extent unit="page">
            <start>12</start>
            <end>23</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment
%A Lin, Geyu
%A Wang, Bin
%A Liu, Zhengyuan
%A Chen, Nancy F.
%S Proceedings of the Second Workshop on Scaling Up Multilingual & Multi-Cultural Evaluation
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi
%F lin-etal-2025-crossin
%X Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those that are linguistically distant from English. This performance discrepancy mainly stems from the imbalanced distribution of training data across languages during pre-training and instruction tuning stages. To address this problem, we propose a novel approach called CrossIn, which utilizes a mixed composition of cross-lingual instruction tuning data. Our method leverages the compressed representation shared by various languages to efficiently enhance the model‘s task-solving capabilities and multilingual proficiency within a single process. In addition, we introduce a multi-task and multi-faceted benchmark to evaluate the effectiveness of CrossIn. Experimental results demonstrate that our method substantially improves performance across tasks and languages, and we provide extensive insights into the impact of cross-lingual data volume and the integration of translation data on enhancing multilingual consistency and accuracy.
%U https://aclanthology.org/2025.sumeval-2.2/
%P 12-23

Markdown (Informal)

[CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment](https://aclanthology.org/2025.sumeval-2.2/) (Lin et al., SUMEval 2025)

• CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment (Lin et al., SUMEval 2025)

ACL

• Geyu Lin, Bin Wang, Zhengyuan Liu, and Nancy F. Chen. 2025. CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment. In Proceedings of the Second Workshop on Scaling Up Multilingual & Multi-Cultural Evaluation, pages 12–23, Abu Dhabi. Association for Computational Linguistics.