@inproceedings{truong-etal-2024-crossing,
title = "Crossing Linguistic Horizons: Finetuning and Comprehensive Evaluation of {V}ietnamese Large Language Models",
author = "Truong, Sang and
Nguyen, Duc and
Nguyen, Toan and
Le, Dong and
Truong, Nhi and
Quan, Tho and
Koyejo, Sanmi",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.182",
pages = "2849--2900",
abstract = "Recent advancements in large language models (LLMs) have underscored their importance in the evolution of artificial intelligence. However, despite extensive pretraining on multilingual datasets, available open-sourced LLMs exhibit limited effectiveness in processing Vietnamese. The challenge is exacerbated by the absence of systematic benchmark datasets and metrics tailored for Vietnamese LLM evaluation. To mitigate these issues, we have finetuned LLMs specifically for Vietnamese and developed a comprehensive evaluation framework encompassing 10 tasks and 31 metrics. We observe that finetuning can help LLMs transfer knowledge across languages, serving as an efficient way to bolster their capabilities in non-English languages. Moreover, our analysis indicates that larger models can introduce more biases and uncalibrated outputs and the key factor influencing LLM performance is the quality of the training or finetuning datasets. These insights underscore the significance of meticulous finetuning with high-quality datasets in enhancing LLM performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="truong-etal-2024-crossing">
<titleInfo>
<title>Crossing Linguistic Horizons: Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sang</namePart>
<namePart type="family">Truong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duc</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toan</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nhi</namePart>
<namePart type="family">Truong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tho</namePart>
<namePart type="family">Quan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanmi</namePart>
<namePart type="family">Koyejo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advancements in large language models (LLMs) have underscored their importance in the evolution of artificial intelligence. However, despite extensive pretraining on multilingual datasets, available open-sourced LLMs exhibit limited effectiveness in processing Vietnamese. The challenge is exacerbated by the absence of systematic benchmark datasets and metrics tailored for Vietnamese LLM evaluation. To mitigate these issues, we have finetuned LLMs specifically for Vietnamese and developed a comprehensive evaluation framework encompassing 10 tasks and 31 metrics. We observe that finetuning can help LLMs transfer knowledge across languages, serving as an efficient way to bolster their capabilities in non-English languages. Moreover, our analysis indicates that larger models can introduce more biases and uncalibrated outputs and the key factor influencing LLM performance is the quality of the training or finetuning datasets. These insights underscore the significance of meticulous finetuning with high-quality datasets in enhancing LLM performance.</abstract>
<identifier type="citekey">truong-etal-2024-crossing</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.182</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>2849</start>
<end>2900</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Crossing Linguistic Horizons: Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models
%A Truong, Sang
%A Nguyen, Duc
%A Nguyen, Toan
%A Le, Dong
%A Truong, Nhi
%A Quan, Tho
%A Koyejo, Sanmi
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F truong-etal-2024-crossing
%X Recent advancements in large language models (LLMs) have underscored their importance in the evolution of artificial intelligence. However, despite extensive pretraining on multilingual datasets, available open-sourced LLMs exhibit limited effectiveness in processing Vietnamese. The challenge is exacerbated by the absence of systematic benchmark datasets and metrics tailored for Vietnamese LLM evaluation. To mitigate these issues, we have finetuned LLMs specifically for Vietnamese and developed a comprehensive evaluation framework encompassing 10 tasks and 31 metrics. We observe that finetuning can help LLMs transfer knowledge across languages, serving as an efficient way to bolster their capabilities in non-English languages. Moreover, our analysis indicates that larger models can introduce more biases and uncalibrated outputs and the key factor influencing LLM performance is the quality of the training or finetuning datasets. These insights underscore the significance of meticulous finetuning with high-quality datasets in enhancing LLM performance.
%U https://aclanthology.org/2024.findings-naacl.182
%P 2849-2900
Markdown (Informal)
[Crossing Linguistic Horizons: Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models](https://aclanthology.org/2024.findings-naacl.182) (Truong et al., Findings 2024)
ACL