<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ki-carpuat-2025-automatic">
    <titleInfo>
        <title>Automatic Input Rewriting Improves Translation with Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dayeon</namePart>
        <namePart type="family">Ki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marine</namePart>
        <namePart type="family">Carpuat</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="family">Chiruzzo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-189-6</identifier>
    </relatedItem>
    <abstract>Can we improve machine translation (MT) with LLMs by rewriting their inputs automatically? Users commonly rely on the intuition that well-written text is easier to translate when using off-the-shelf MT systems. LLMs can rewrite text in many ways but in the context of MT, these capabilities have been primarily exploited to rewrite outputs via post-editing. We present an empirical study of 21 input rewriting methods with 3 open-weight LLMs for translating from English into 6 target languages. We show that text simplification is the most effective MT-agnostic rewrite strategy and that it can be improved further when using quality estimation to assess translatability. Human evaluation further confirms that simplified rewrites and their MT outputs both largely preserve the original meaning of the source and MT. These results suggest LLM-assisted input rewriting as a promising direction for improving translations.</abstract>
    <identifier type="citekey">ki-carpuat-2025-automatic</identifier>
    <identifier type="doi">10.18653/v1/2025.naacl-long.542</identifier>
    <location>
        <url>https://aclanthology.org/2025.naacl-long.542/</url>
    </location>
    <part>
        <date>2025-04</date>
        <extent unit="page">
            <start>10829</start>
            <end>10856</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Automatic Input Rewriting Improves Translation with Large Language Models
%A Ki, Dayeon
%A Carpuat, Marine
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F ki-carpuat-2025-automatic
%X Can we improve machine translation (MT) with LLMs by rewriting their inputs automatically? Users commonly rely on the intuition that well-written text is easier to translate when using off-the-shelf MT systems. LLMs can rewrite text in many ways but in the context of MT, these capabilities have been primarily exploited to rewrite outputs via post-editing. We present an empirical study of 21 input rewriting methods with 3 open-weight LLMs for translating from English into 6 target languages. We show that text simplification is the most effective MT-agnostic rewrite strategy and that it can be improved further when using quality estimation to assess translatability. Human evaluation further confirms that simplified rewrites and their MT outputs both largely preserve the original meaning of the source and MT. These results suggest LLM-assisted input rewriting as a promising direction for improving translations.
%R 10.18653/v1/2025.naacl-long.542
%U https://aclanthology.org/2025.naacl-long.542/
%U https://doi.org/10.18653/v1/2025.naacl-long.542
%P 10829-10856

Markdown (Informal)

[Automatic Input Rewriting Improves Translation with Large Language Models](https://aclanthology.org/2025.naacl-long.542/) (Ki & Carpuat, NAACL 2025)

• Automatic Input Rewriting Improves Translation with Large Language Models (Ki & Carpuat, NAACL 2025)

ACL

• Dayeon Ki and Marine Carpuat. 2025. Automatic Input Rewriting Improves Translation with Large Language Models. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 10829–10856, Albuquerque, New Mexico. Association for Computational Linguistics.