@inproceedings{sun-etal-2025-fine,
title = "Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation",
author = "Sun, Yirong and
Zhu, Dawei and
Chen, Yanjun and
Xiao, Erjia and
Chen, Xinghao and
Shen, Xiaoyu",
editor = "Ebrahimi, Abteen and
Haider, Samar and
Liu, Emmy and
Haider, Sammar and
Leonor Pacheco, Maria and
Wein, Shira",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = apr,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-srw.1/",
pages = "1--17",
ISBN = "979-8-89176-192-6",
abstract = "Large language models (LLMs) have excelled in various NLP tasks, including machine translation (MT), yet most studies focus on sentence-level translation. This work investigates the inherent capability of instruction-tuned LLMs for document-level translation (docMT). Unlike prior approaches that require specialized techniques, we evaluate LLMs by directly prompting them to translate entire documents in a single pass. Our results show that this method improves translation quality compared to translating sentences separately, even without document-level fine-tuning. However, this advantage is not reflected in BLEU scores, which often favor sentence-based translations. We propose using the LLM-as-a-judge paradigm for evaluation, where GPT-4 is used to assess document coherence, accuracy, and fluency in a more nuanced way than n-gram-based metrics. Overall, our work demonstrates that instruction-tuned LLMs can effectively leverage document context for translation. However, we caution against using BLEU scores for evaluating docMT, as they often provide misleading outcomes, failing to capture the quality of document-level translation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2025-fine">
<titleInfo>
<title>Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yirong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawei</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanjun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erjia</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinghao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Shen</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 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sammar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Leonor Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shira</namePart>
<namePart type="family">Wein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-192-6</identifier>
</relatedItem>
<abstract>Large language models (LLMs) have excelled in various NLP tasks, including machine translation (MT), yet most studies focus on sentence-level translation. This work investigates the inherent capability of instruction-tuned LLMs for document-level translation (docMT). Unlike prior approaches that require specialized techniques, we evaluate LLMs by directly prompting them to translate entire documents in a single pass. Our results show that this method improves translation quality compared to translating sentences separately, even without document-level fine-tuning. However, this advantage is not reflected in BLEU scores, which often favor sentence-based translations. We propose using the LLM-as-a-judge paradigm for evaluation, where GPT-4 is used to assess document coherence, accuracy, and fluency in a more nuanced way than n-gram-based metrics. Overall, our work demonstrates that instruction-tuned LLMs can effectively leverage document context for translation. However, we caution against using BLEU scores for evaluating docMT, as they often provide misleading outcomes, failing to capture the quality of document-level translation.</abstract>
<identifier type="citekey">sun-etal-2025-fine</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-srw.1/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>1</start>
<end>17</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation
%A Sun, Yirong
%A Zhu, Dawei
%A Chen, Yanjun
%A Xiao, Erjia
%A Chen, Xinghao
%A Shen, Xiaoyu
%Y Ebrahimi, Abteen
%Y Haider, Samar
%Y Liu, Emmy
%Y Haider, Sammar
%Y Leonor Pacheco, Maria
%Y Wein, Shira
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-192-6
%F sun-etal-2025-fine
%X Large language models (LLMs) have excelled in various NLP tasks, including machine translation (MT), yet most studies focus on sentence-level translation. This work investigates the inherent capability of instruction-tuned LLMs for document-level translation (docMT). Unlike prior approaches that require specialized techniques, we evaluate LLMs by directly prompting them to translate entire documents in a single pass. Our results show that this method improves translation quality compared to translating sentences separately, even without document-level fine-tuning. However, this advantage is not reflected in BLEU scores, which often favor sentence-based translations. We propose using the LLM-as-a-judge paradigm for evaluation, where GPT-4 is used to assess document coherence, accuracy, and fluency in a more nuanced way than n-gram-based metrics. Overall, our work demonstrates that instruction-tuned LLMs can effectively leverage document context for translation. However, we caution against using BLEU scores for evaluating docMT, as they often provide misleading outcomes, failing to capture the quality of document-level translation.
%U https://aclanthology.org/2025.naacl-srw.1/
%P 1-17
Markdown (Informal)
[Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation](https://aclanthology.org/2025.naacl-srw.1/) (Sun et al., NAACL 2025)
ACL
- Yirong Sun, Dawei Zhu, Yanjun Chen, Erjia Xiao, Xinghao Chen, and Xiaoyu Shen. 2025. Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 1–17, Albuquerque, USA. Association for Computational Linguistics.