<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2025-exploring">
    <titleInfo>
        <title>Exploring In-context Example Generation for Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dohyun</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seungil</namePart>
        <namePart type="given">Chad</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chanwoo</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yujin</namePart>
        <namePart type="family">Baek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jaegul</namePart>
        <namePart type="family">Choo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) have demonstrated strong performance across various tasks, leveraging their exceptional in-context learning ability with only a few examples.Accordingly, the selection of optimal in-context examples has been actively studied in the field of machine translation.However, these studies presuppose the presence of a demonstration pool with human-annotated pairs, making them less applicable to low-resource languages where such an assumption is challenging to meet.To overcome this limitation, this paper explores the research direction of in-context example generation for machine translation.Specifically, we propose Demonstration Augmentation for Translation (DAT), a simple yet effective approach that generates example pairs without relying on any external resources.This method builds upon two prior criteria, relevance and diversity, which have been highlighted in previous work as key factors for in-context example selection.Through experiments and analysis on low-resource languages where human-annotated pairs are scarce, we show that DAT achieves superior translation quality compared to the baselines.Furthermore, we investigate the potential of progressively accumulating generated pairs during test time to build and reuse a demonstration pool. Our implementation is publicly available at https://github.com/aiclaudev/DAT.</abstract>
    <identifier type="citekey">lee-etal-2025-exploring</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.1362</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.1362/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>26554</start>
            <end>26568</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Exploring In-context Example Generation for Machine Translation
%A Lee, Dohyun
%A Lee, Seungil Chad
%A Yang, Chanwoo
%A Baek, Yujin
%A Choo, Jaegul
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F lee-etal-2025-exploring
%X Large language models (LLMs) have demonstrated strong performance across various tasks, leveraging their exceptional in-context learning ability with only a few examples.Accordingly, the selection of optimal in-context examples has been actively studied in the field of machine translation.However, these studies presuppose the presence of a demonstration pool with human-annotated pairs, making them less applicable to low-resource languages where such an assumption is challenging to meet.To overcome this limitation, this paper explores the research direction of in-context example generation for machine translation.Specifically, we propose Demonstration Augmentation for Translation (DAT), a simple yet effective approach that generates example pairs without relying on any external resources.This method builds upon two prior criteria, relevance and diversity, which have been highlighted in previous work as key factors for in-context example selection.Through experiments and analysis on low-resource languages where human-annotated pairs are scarce, we show that DAT achieves superior translation quality compared to the baselines.Furthermore, we investigate the potential of progressively accumulating generated pairs during test time to build and reuse a demonstration pool. Our implementation is publicly available at https://github.com/aiclaudev/DAT.
%R 10.18653/v1/2025.findings-acl.1362
%U https://aclanthology.org/2025.findings-acl.1362/
%U https://doi.org/10.18653/v1/2025.findings-acl.1362
%P 26554-26568

Markdown (Informal)

[Exploring In-context Example Generation for Machine Translation](https://aclanthology.org/2025.findings-acl.1362/) (Lee et al., Findings 2025)

• Exploring In-context Example Generation for Machine Translation (Lee et al., Findings 2025)

ACL

• Dohyun Lee, Seungil Chad Lee, Chanwoo Yang, Yujin Baek, and Jaegul Choo. 2025. Exploring In-context Example Generation for Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2025, pages 26554–26568, Vienna, Austria. Association for Computational Linguistics.