@article{pang-etal-2025-salute,
title = "Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models",
author = "Pang, Jianhui and
Ye, Fanghua and
Wong, Derek Fai and
Yu, Dian and
Shi, Shuming and
Tu, Zhaopeng and
Wang, Longyue",
journal = "Transactions of the Association for Computational Linguistics",
volume = "13",
year = "2025",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2025.tacl-1.4/",
doi = "10.1162/tacl_a_00730",
pages = "73--95",
abstract = "The evolution of Neural Machine Translation (NMT) has been significantly influenced by six core challenges (Koehn and Knowles, 2017) that have acted as benchmarks for progress in this field. This study revisits these challenges, offering insights into their ongoing relevance in the context of advanced Large Language Models (LLMs): domain mismatch, amount of parallel data, rare word prediction, translation of long sentences, attention model as word alignment, and sub-optimal beam search. Our empirical findings show that LLMs effectively reduce reliance on parallel data for major languages during pretraining and significantly improve translation of long sentences containing approximately 80 words, even translating documents up to 512 words. Despite these improvements, challenges in domain mismatch and rare word prediction persist. While NMT-specific challenges like word alignment and beam search may not apply to LLMs, we identify three new challenges in LLM-based translation: inference efficiency, translation of low-resource languages during pretraining, and human-aligned evaluation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pang-etal-2025-salute">
<titleInfo>
<title>Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianhui</namePart>
<namePart type="family">Pang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fanghua</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dian</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaopeng</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longyue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>The evolution of Neural Machine Translation (NMT) has been significantly influenced by six core challenges (Koehn and Knowles, 2017) that have acted as benchmarks for progress in this field. This study revisits these challenges, offering insights into their ongoing relevance in the context of advanced Large Language Models (LLMs): domain mismatch, amount of parallel data, rare word prediction, translation of long sentences, attention model as word alignment, and sub-optimal beam search. Our empirical findings show that LLMs effectively reduce reliance on parallel data for major languages during pretraining and significantly improve translation of long sentences containing approximately 80 words, even translating documents up to 512 words. Despite these improvements, challenges in domain mismatch and rare word prediction persist. While NMT-specific challenges like word alignment and beam search may not apply to LLMs, we identify three new challenges in LLM-based translation: inference efficiency, translation of low-resource languages during pretraining, and human-aligned evaluation.</abstract>
<identifier type="citekey">pang-etal-2025-salute</identifier>
<identifier type="doi">10.1162/tacl_a_00730</identifier>
<location>
<url>https://aclanthology.org/2025.tacl-1.4/</url>
</location>
<part>
<date>2025</date>
<detail type="volume"><number>13</number></detail>
<extent unit="page">
<start>73</start>
<end>95</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models
%A Pang, Jianhui
%A Ye, Fanghua
%A Wong, Derek Fai
%A Yu, Dian
%A Shi, Shuming
%A Tu, Zhaopeng
%A Wang, Longyue
%J Transactions of the Association for Computational Linguistics
%D 2025
%V 13
%I MIT Press
%C Cambridge, MA
%F pang-etal-2025-salute
%X The evolution of Neural Machine Translation (NMT) has been significantly influenced by six core challenges (Koehn and Knowles, 2017) that have acted as benchmarks for progress in this field. This study revisits these challenges, offering insights into their ongoing relevance in the context of advanced Large Language Models (LLMs): domain mismatch, amount of parallel data, rare word prediction, translation of long sentences, attention model as word alignment, and sub-optimal beam search. Our empirical findings show that LLMs effectively reduce reliance on parallel data for major languages during pretraining and significantly improve translation of long sentences containing approximately 80 words, even translating documents up to 512 words. Despite these improvements, challenges in domain mismatch and rare word prediction persist. While NMT-specific challenges like word alignment and beam search may not apply to LLMs, we identify three new challenges in LLM-based translation: inference efficiency, translation of low-resource languages during pretraining, and human-aligned evaluation.
%R 10.1162/tacl_a_00730
%U https://aclanthology.org/2025.tacl-1.4/
%U https://doi.org/10.1162/tacl_a_00730
%P 73-95
Markdown (Informal)
[Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models](https://aclanthology.org/2025.tacl-1.4/) (Pang et al., TACL 2025)
ACL