<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="javorsky-etal-2025-prompting">
    <titleInfo>
        <title>Prompting LLMs: Length Control for Isometric Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dávid</namePart>
        <namePart type="family">Javorský</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ondřej</namePart>
        <namePart type="family">Bojar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">François</namePart>
        <namePart type="family">Yvon</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>Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Elizabeth</namePart>
            <namePart type="family">Salesky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marcello</namePart>
            <namePart type="family">Federico</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonis</namePart>
            <namePart type="family">Anastasopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria (in-person and online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-272-5</identifier>
    </relatedItem>
    <abstract>In this study, we explore the effectiveness of isometric machine translation across multiple language pairs (EnoDe, EnoFr, and EnoEs) under the conditions of the IWSLT Isometric Shared Task 2022. Using eight open-source large language models (LLMs) of varying sizes, we investigate how different prompting strategies, varying numbers of few-shot examples, and demonstration selection influence translation quality and length control. We discover that the phrasing of instructions, when aligned with the properties of the provided demonstrations, plays a crucial role in controlling the output length. Our experiments show that LLMs tend to produce shorter translations only when presented with extreme examples, while isometric demonstrations often lead to the models disregarding length constraints. While few-shot prompting generally enhances translation quality, further improvements are marginal across 5, 10, and 20-shot settings. Finally, considering multiple outputs allows to notably improve overall tradeoff between the length and quality, yielding state-of-the-art performance for some language pairs.</abstract>
    <identifier type="citekey">javorsky-etal-2025-prompting</identifier>
    <identifier type="doi">10.18653/v1/2025.iwslt-1.11</identifier>
    <location>
        <url>https://aclanthology.org/2025.iwslt-1.11/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>119</start>
            <end>137</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Prompting LLMs: Length Control for Isometric Machine Translation
%A Javorský, Dávid
%A Bojar, Ondřej
%A Yvon, François
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Anastasopoulos, Antonis
%S Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria (in-person and online)
%@ 979-8-89176-272-5
%F javorsky-etal-2025-prompting
%X In this study, we explore the effectiveness of isometric machine translation across multiple language pairs (EnoDe, EnoFr, and EnoEs) under the conditions of the IWSLT Isometric Shared Task 2022. Using eight open-source large language models (LLMs) of varying sizes, we investigate how different prompting strategies, varying numbers of few-shot examples, and demonstration selection influence translation quality and length control. We discover that the phrasing of instructions, when aligned with the properties of the provided demonstrations, plays a crucial role in controlling the output length. Our experiments show that LLMs tend to produce shorter translations only when presented with extreme examples, while isometric demonstrations often lead to the models disregarding length constraints. While few-shot prompting generally enhances translation quality, further improvements are marginal across 5, 10, and 20-shot settings. Finally, considering multiple outputs allows to notably improve overall tradeoff between the length and quality, yielding state-of-the-art performance for some language pairs.
%R 10.18653/v1/2025.iwslt-1.11
%U https://aclanthology.org/2025.iwslt-1.11/
%U https://doi.org/10.18653/v1/2025.iwslt-1.11
%P 119-137

Markdown (Informal)

[Prompting LLMs: Length Control for Isometric Machine Translation](https://aclanthology.org/2025.iwslt-1.11/) (Javorský et al., IWSLT 2025)

• Prompting LLMs: Length Control for Isometric Machine Translation (Javorský et al., IWSLT 2025)

ACL

• Dávid Javorský, Ondřej Bojar, and François Yvon. 2025. Prompting LLMs: Length Control for Isometric Machine Translation. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 119–137, Vienna, Austria (in-person and online). Association for Computational Linguistics.