@inproceedings{li-etal-2024-towards-demonstration,
title = "Towards Demonstration-Aware Large Language Models for Machine Translation",
author = "Li, Chen and
Zhang, Meishan and
Liu, Xuebo and
Li, Zhaocong and
Wong, Derek and
Zhang, Min",
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.824",
doi = "10.18653/v1/2024.findings-acl.824",
pages = "13868--13881",
abstract = "Tuning-based large language models for machine translation (aka large translation model, LTM) have demonstrated significant performance in the field of machine translation. Despite their success, these models often face difficulties in leveraging demonstrations to further improve their performance. To tackle this challenge, we introduce a novel approach that integrates demonstration-aware training and inference strategies within the framework of tuning-based LTMs, hereby referred to as demonstration-aware LTMs. During training, we enrich the model{'}s learning process by incorporating both sentence- and document-level demonstrations derived from its original training dataset. During inference, the model synergizes its own contextual translations with retrieved high-quality demonstrations, leading to more precise and contextually appropriate outputs. Empirical results reveal that our demonstration-aware LTM not only mitigates the negative impacts traditionally associated with demonstrations but also secures substantial improvements in translation accuracy, particularly in domain-specific and document-level translation tasks. Source code and scripts are freely available at https://github.com/ChenLi0620/Demo-Aware-LLM-MT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-towards-demonstration">
<titleInfo>
<title>Towards Demonstration-Aware Large Language Models for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meishan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuebo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaocong</namePart>
<namePart type="family">Li</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">Min</namePart>
<namePart type="family">Zhang</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>Tuning-based large language models for machine translation (aka large translation model, LTM) have demonstrated significant performance in the field of machine translation. Despite their success, these models often face difficulties in leveraging demonstrations to further improve their performance. To tackle this challenge, we introduce a novel approach that integrates demonstration-aware training and inference strategies within the framework of tuning-based LTMs, hereby referred to as demonstration-aware LTMs. During training, we enrich the model’s learning process by incorporating both sentence- and document-level demonstrations derived from its original training dataset. During inference, the model synergizes its own contextual translations with retrieved high-quality demonstrations, leading to more precise and contextually appropriate outputs. Empirical results reveal that our demonstration-aware LTM not only mitigates the negative impacts traditionally associated with demonstrations but also secures substantial improvements in translation accuracy, particularly in domain-specific and document-level translation tasks. Source code and scripts are freely available at https://github.com/ChenLi0620/Demo-Aware-LLM-MT.</abstract>
<identifier type="citekey">li-etal-2024-towards-demonstration</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.824</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.824</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13868</start>
<end>13881</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Demonstration-Aware Large Language Models for Machine Translation
%A Li, Chen
%A Zhang, Meishan
%A Liu, Xuebo
%A Li, Zhaocong
%A Wong, Derek
%A Zhang, Min
%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 li-etal-2024-towards-demonstration
%X Tuning-based large language models for machine translation (aka large translation model, LTM) have demonstrated significant performance in the field of machine translation. Despite their success, these models often face difficulties in leveraging demonstrations to further improve their performance. To tackle this challenge, we introduce a novel approach that integrates demonstration-aware training and inference strategies within the framework of tuning-based LTMs, hereby referred to as demonstration-aware LTMs. During training, we enrich the model’s learning process by incorporating both sentence- and document-level demonstrations derived from its original training dataset. During inference, the model synergizes its own contextual translations with retrieved high-quality demonstrations, leading to more precise and contextually appropriate outputs. Empirical results reveal that our demonstration-aware LTM not only mitigates the negative impacts traditionally associated with demonstrations but also secures substantial improvements in translation accuracy, particularly in domain-specific and document-level translation tasks. Source code and scripts are freely available at https://github.com/ChenLi0620/Demo-Aware-LLM-MT.
%R 10.18653/v1/2024.findings-acl.824
%U https://aclanthology.org/2024.findings-acl.824
%U https://doi.org/10.18653/v1/2024.findings-acl.824
%P 13868-13881
Markdown (Informal)
[Towards Demonstration-Aware Large Language Models for Machine Translation](https://aclanthology.org/2024.findings-acl.824) (Li et al., Findings 2024)
ACL