<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohammed-etal-2026-unlocking">
    <titleInfo>
        <title>Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wafaa</namePart>
        <namePart type="family">Mohammed</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vlad</namePart>
        <namePart type="family">Niculae</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chrysoula</namePart>
        <namePart type="family">Zerva</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-380-7</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) have emerged as strong contenders in machine translation. Yet, they still struggle to adequately handle discourse phenomena, such as pronoun resolution and lexical cohesion at the document level. In this study, we thoroughly investigate the discourse phenomena performance of LLMs in context-aware translation. We demonstrate that discourse knowledge is encoded within LLMs and propose the use of quality-aware decoding (QAD), specifically minimum Bayes risk decoding, to effectively extract this knowledge, showcasing its superiority over other decoding approaches through comprehensive analysis. Furthermore, we illustrate that QAD enhances the semantic richness of translations and aligns them more closely with human preferences.</abstract>
    <identifier type="citekey">mohammed-etal-2026-unlocking</identifier>
    <location>
        <url>https://aclanthology.org/2026.eacl-long.220/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>4752</start>
            <end>4774</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding
%A Mohammed, Wafaa
%A Niculae, Vlad
%A Zerva, Chrysoula
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F mohammed-etal-2026-unlocking
%X Large language models (LLMs) have emerged as strong contenders in machine translation. Yet, they still struggle to adequately handle discourse phenomena, such as pronoun resolution and lexical cohesion at the document level. In this study, we thoroughly investigate the discourse phenomena performance of LLMs in context-aware translation. We demonstrate that discourse knowledge is encoded within LLMs and propose the use of quality-aware decoding (QAD), specifically minimum Bayes risk decoding, to effectively extract this knowledge, showcasing its superiority over other decoding approaches through comprehensive analysis. Furthermore, we illustrate that QAD enhances the semantic richness of translations and aligns them more closely with human preferences.
%U https://aclanthology.org/2026.eacl-long.220/
%P 4752-4774

Markdown (Informal)

[Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding](https://aclanthology.org/2026.eacl-long.220/) (Mohammed et al., EACL 2026)

• Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding (Mohammed et al., EACL 2026)

ACL

• Wafaa Mohammed, Vlad Niculae, and Chrysoula Zerva. 2026. Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4752–4774, Rabat, Morocco. Association for Computational Linguistics.