@inproceedings{wang-etal-2024-benchmarking,
title = "Benchmarking and Improving Long-Text Translation with Large Language Models",
author = "Wang, Longyue and
Du, Zefeng and
Jiao, Wenxiang and
Lyu, Chenyang and
Pang, Jianhui and
Cui, Leyang and
Song, Kaiqiang and
Wong, Derek and
Shi, Shuming and
Tu, Zhaopeng",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.428/",
doi = "10.18653/v1/2024.findings-acl.428",
pages = "7175--7187",
abstract = "Recent studies have illuminated the promising capabilities of large language models (LLMs) in handling long texts. However, their performance in machine translation (MT) of long documents remains underexplored. This paper aims to shed light on how LLMs navigate this complex task, offering a comprehensive evaluation of their capabilities and limitations in long-text MT. First, we collect and construct an instruction-based benchmark dataset, specifically designed for the finetuning and evaluation of LLMs, encompassing multilingual, multi-domain, and document-level parallel data. Second, we conduct a comprehensive comparison between MT and LLM models concerning document-level translation. Our analysis uncovers that LLMs exhibit shortcomings in long-text domains, and their performance diminishes as document size escalates. By exploiting various extrapolation strategies, we enhance the capacity of LLMs to translate longer texts. We release data, code, and models at https://github.com/longyuewangdcu/Document-MT-LLM."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-benchmarking">
<titleInfo>
<title>Benchmarking and Improving Long-Text Translation with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Longyue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zefeng</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenxiang</namePart>
<namePart type="family">Jiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenyang</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Leyang</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaiqiang</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="family">Wong</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>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent studies have illuminated the promising capabilities of large language models (LLMs) in handling long texts. However, their performance in machine translation (MT) of long documents remains underexplored. This paper aims to shed light on how LLMs navigate this complex task, offering a comprehensive evaluation of their capabilities and limitations in long-text MT. First, we collect and construct an instruction-based benchmark dataset, specifically designed for the finetuning and evaluation of LLMs, encompassing multilingual, multi-domain, and document-level parallel data. Second, we conduct a comprehensive comparison between MT and LLM models concerning document-level translation. Our analysis uncovers that LLMs exhibit shortcomings in long-text domains, and their performance diminishes as document size escalates. By exploiting various extrapolation strategies, we enhance the capacity of LLMs to translate longer texts. We release data, code, and models at https://github.com/longyuewangdcu/Document-MT-LLM.</abstract>
<identifier type="citekey">wang-etal-2024-benchmarking</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.428</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.428/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>7175</start>
<end>7187</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking and Improving Long-Text Translation with Large Language Models
%A Wang, Longyue
%A Du, Zefeng
%A Jiao, Wenxiang
%A Lyu, Chenyang
%A Pang, Jianhui
%A Cui, Leyang
%A Song, Kaiqiang
%A Wong, Derek
%A Shi, Shuming
%A Tu, Zhaopeng
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wang-etal-2024-benchmarking
%X Recent studies have illuminated the promising capabilities of large language models (LLMs) in handling long texts. However, their performance in machine translation (MT) of long documents remains underexplored. This paper aims to shed light on how LLMs navigate this complex task, offering a comprehensive evaluation of their capabilities and limitations in long-text MT. First, we collect and construct an instruction-based benchmark dataset, specifically designed for the finetuning and evaluation of LLMs, encompassing multilingual, multi-domain, and document-level parallel data. Second, we conduct a comprehensive comparison between MT and LLM models concerning document-level translation. Our analysis uncovers that LLMs exhibit shortcomings in long-text domains, and their performance diminishes as document size escalates. By exploiting various extrapolation strategies, we enhance the capacity of LLMs to translate longer texts. We release data, code, and models at https://github.com/longyuewangdcu/Document-MT-LLM.
%R 10.18653/v1/2024.findings-acl.428
%U https://aclanthology.org/2024.findings-acl.428/
%U https://doi.org/10.18653/v1/2024.findings-acl.428
%P 7175-7187
Markdown (Informal)
[Benchmarking and Improving Long-Text Translation with Large Language Models](https://aclanthology.org/2024.findings-acl.428/) (Wang et al., Findings 2024)
ACL
- Longyue Wang, Zefeng Du, Wenxiang Jiao, Chenyang Lyu, Jianhui Pang, Leyang Cui, Kaiqiang Song, Derek Wong, Shuming Shi, and Zhaopeng Tu. 2024. Benchmarking and Improving Long-Text Translation with Large Language Models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 7175–7187, Bangkok, Thailand. Association for Computational Linguistics.