<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sennrich-etal-2024-mitigating">
    <titleInfo>
        <title>Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rico</namePart>
        <namePart type="family">Sennrich</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jannis</namePart>
        <namePart type="family">Vamvas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alireza</namePart>
        <namePart type="family">Mohammadshahi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yvette</namePart>
            <namePart type="family">Graham</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Matthew</namePart>
            <namePart type="family">Purver</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">St. Julian’s, Malta</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Hallucinations and off-target translation remain unsolved problems in MT, especially for low-resource languages and massively multilingual models. In this paper, we introduce two related methods to mitigate these failure cases with a modified decoding objective, without either requiring retraining or external models. In source-contrastive decoding, we search for a translation that is probable given the correct input, but improbable given a random input segment. In language-contrastive decoding, we search for a translation that is probable, but improbable given the wrong language indicator token. Experiments on the massively multilingual models M2M-100 (418M) and SMaLL-100 show that these methods suppress hallucinations and off-target translations, reducing the number of translations with segment-level chrF2 below 10 by 67-83% on average across 57 tested translation directions. In a proof of concept on out-of-English translation, we also show that we can suppress off-target translations with large language models. We release code upon acceptance.</abstract>
    <identifier type="citekey">sennrich-etal-2024-mitigating</identifier>
    <location>
        <url>https://aclanthology.org/2024.eacl-short.4</url>
    </location>
    <part>
        <date>2024-03</date>
        <extent unit="page">
            <start>21</start>
            <end>33</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding
%A Sennrich, Rico
%A Vamvas, Jannis
%A Mohammadshahi, Alireza
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F sennrich-etal-2024-mitigating
%X Hallucinations and off-target translation remain unsolved problems in MT, especially for low-resource languages and massively multilingual models. In this paper, we introduce two related methods to mitigate these failure cases with a modified decoding objective, without either requiring retraining or external models. In source-contrastive decoding, we search for a translation that is probable given the correct input, but improbable given a random input segment. In language-contrastive decoding, we search for a translation that is probable, but improbable given the wrong language indicator token. Experiments on the massively multilingual models M2M-100 (418M) and SMaLL-100 show that these methods suppress hallucinations and off-target translations, reducing the number of translations with segment-level chrF2 below 10 by 67-83% on average across 57 tested translation directions. In a proof of concept on out-of-English translation, we also show that we can suppress off-target translations with large language models. We release code upon acceptance.
%U https://aclanthology.org/2024.eacl-short.4
%P 21-33

Markdown (Informal)

[Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding](https://aclanthology.org/2024.eacl-short.4) (Sennrich et al., EACL 2024)

• Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding (Sennrich et al., EACL 2024)

ACL

• Rico Sennrich, Jannis Vamvas, and Alireza Mohammadshahi. 2024. Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 21–33, St. Julian’s, Malta. Association for Computational Linguistics.