@inproceedings{lu-etal-2025-low,
title = "Low-Resource Language Expansion and Translation Capacity Enhancement for {LLM}: A Study on the {U}yghur",
author = "Lu, Kaiwen and
Yang, Yating and
Yang, Fengyi and
Dong, Rui and
Ma, Bo and
Aihemaiti, Aihetamujiang and
Atawulla, Abibilla and
Wang, Lei and
Zhou, Xi",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.559/",
pages = "8360--8373",
abstract = "Although large language models have significantly advanced natural language generation, their potential in low-resource machine translation has not yet been fully explored, especially for languages that translation models have not been trained on. In this study, we provide a detailed demonstration of how to efficiently expand low-resource languages for large language models and significantly enhance the model`s translation ability, using Uyghur as an example. The process involves four stages: collecting and pre-processing monolingual data, conducting continuous pre-training with extensive monolingual data, fine-tuning with less parallel corpora using translation supervision, and proposing a direct preference optimization based on translation self-evolution (DPOSE) on this basis. Extensive experiments have shown that our strategy effectively expands the low-resource languages supported by large language models and significantly enhances the model`s translation ability in Uyghur with less parallel data. Our research provides detailed insights for expanding other low-resource languages into large language models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2025-low">
<titleInfo>
<title>Low-Resource Language Expansion and Translation Capacity Enhancement for LLM: A Study on the Uyghur</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kaiwen</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yating</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fengyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aihetamujiang</namePart>
<namePart type="family">Aihemaiti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abibilla</namePart>
<namePart type="family">Atawulla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although large language models have significantly advanced natural language generation, their potential in low-resource machine translation has not yet been fully explored, especially for languages that translation models have not been trained on. In this study, we provide a detailed demonstration of how to efficiently expand low-resource languages for large language models and significantly enhance the model‘s translation ability, using Uyghur as an example. The process involves four stages: collecting and pre-processing monolingual data, conducting continuous pre-training with extensive monolingual data, fine-tuning with less parallel corpora using translation supervision, and proposing a direct preference optimization based on translation self-evolution (DPOSE) on this basis. Extensive experiments have shown that our strategy effectively expands the low-resource languages supported by large language models and significantly enhances the model‘s translation ability in Uyghur with less parallel data. Our research provides detailed insights for expanding other low-resource languages into large language models.</abstract>
<identifier type="citekey">lu-etal-2025-low</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.559/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>8360</start>
<end>8373</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Low-Resource Language Expansion and Translation Capacity Enhancement for LLM: A Study on the Uyghur
%A Lu, Kaiwen
%A Yang, Yating
%A Yang, Fengyi
%A Dong, Rui
%A Ma, Bo
%A Aihemaiti, Aihetamujiang
%A Atawulla, Abibilla
%A Wang, Lei
%A Zhou, Xi
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F lu-etal-2025-low
%X Although large language models have significantly advanced natural language generation, their potential in low-resource machine translation has not yet been fully explored, especially for languages that translation models have not been trained on. In this study, we provide a detailed demonstration of how to efficiently expand low-resource languages for large language models and significantly enhance the model‘s translation ability, using Uyghur as an example. The process involves four stages: collecting and pre-processing monolingual data, conducting continuous pre-training with extensive monolingual data, fine-tuning with less parallel corpora using translation supervision, and proposing a direct preference optimization based on translation self-evolution (DPOSE) on this basis. Extensive experiments have shown that our strategy effectively expands the low-resource languages supported by large language models and significantly enhances the model‘s translation ability in Uyghur with less parallel data. Our research provides detailed insights for expanding other low-resource languages into large language models.
%U https://aclanthology.org/2025.coling-main.559/
%P 8360-8373
Markdown (Informal)
[Low-Resource Language Expansion and Translation Capacity Enhancement for LLM: A Study on the Uyghur](https://aclanthology.org/2025.coling-main.559/) (Lu et al., COLING 2025)
ACL
- Kaiwen Lu, Yating Yang, Fengyi Yang, Rui Dong, Bo Ma, Aihetamujiang Aihemaiti, Abibilla Atawulla, Lei Wang, and Xi Zhou. 2025. Low-Resource Language Expansion and Translation Capacity Enhancement for LLM: A Study on the Uyghur. In Proceedings of the 31st International Conference on Computational Linguistics, pages 8360–8373, Abu Dhabi, UAE. Association for Computational Linguistics.