@inproceedings{aur-etal-2026-exploring,
title = "Exploring the Impact of Document Context on {LLM}-based Machine Translation Evaluation",
author = "Aur, Marina Iuliana and
Perrella, Stefano and
Navigli, Roberto",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1839/",
pages = "39253--39276",
ISBN = "979-8-89176-462-0",
abstract = "Human annotators typically assess translation quality by considering the broader document context, which allows them to detect errors arising from discourse-level phenomena that may be missed when evaluating text segments in isolation. However, the role of document-level context in automatic Machine Translation (MT) evaluation remains underexplored. In this work, we present a controlled study of the impact of document context on LLM-based MT evaluation and its interaction with the availability of manually curated references. We consider several evaluation configurations, also exploring how performance varies when enabling the thinking inference mode and conducting task-specific fine-tuning. Our results show that the effect of document context differs substantially across test sets, and that input repetition itself can account for part of the apparent gains. Fine-tuning improves performance consistently and offers larger gains when document context is available, suggesting that task-specific adaptation may help models to handle document-level context more effectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aur-etal-2026-exploring">
<titleInfo>
<title>Exploring the Impact of Document Context on LLM-based Machine Translation Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="given">Iuliana</namePart>
<namePart type="family">Aur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefano</namePart>
<namePart type="family">Perrella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Human annotators typically assess translation quality by considering the broader document context, which allows them to detect errors arising from discourse-level phenomena that may be missed when evaluating text segments in isolation. However, the role of document-level context in automatic Machine Translation (MT) evaluation remains underexplored. In this work, we present a controlled study of the impact of document context on LLM-based MT evaluation and its interaction with the availability of manually curated references. We consider several evaluation configurations, also exploring how performance varies when enabling the thinking inference mode and conducting task-specific fine-tuning. Our results show that the effect of document context differs substantially across test sets, and that input repetition itself can account for part of the apparent gains. Fine-tuning improves performance consistently and offers larger gains when document context is available, suggesting that task-specific adaptation may help models to handle document-level context more effectively.</abstract>
<identifier type="citekey">aur-etal-2026-exploring</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1839/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>39253</start>
<end>39276</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the Impact of Document Context on LLM-based Machine Translation Evaluation
%A Aur, Marina Iuliana
%A Perrella, Stefano
%A Navigli, Roberto
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F aur-etal-2026-exploring
%X Human annotators typically assess translation quality by considering the broader document context, which allows them to detect errors arising from discourse-level phenomena that may be missed when evaluating text segments in isolation. However, the role of document-level context in automatic Machine Translation (MT) evaluation remains underexplored. In this work, we present a controlled study of the impact of document context on LLM-based MT evaluation and its interaction with the availability of manually curated references. We consider several evaluation configurations, also exploring how performance varies when enabling the thinking inference mode and conducting task-specific fine-tuning. Our results show that the effect of document context differs substantially across test sets, and that input repetition itself can account for part of the apparent gains. Fine-tuning improves performance consistently and offers larger gains when document context is available, suggesting that task-specific adaptation may help models to handle document-level context more effectively.
%U https://aclanthology.org/2026.findings-emnlp.1839/
%P 39253-39276
Markdown (Informal)
[Exploring the Impact of Document Context on LLM-based Machine Translation Evaluation](https://aclanthology.org/2026.findings-emnlp.1839/) (Aur et al., Findings 2026)
ACL