@inproceedings{nguyen-etal-2023-vigptqa,
title = "{V}i{GPTQA} - State-of-the-Art {LLM}s for {V}ietnamese Question Answering: System Overview, Core Models Training, and Evaluations",
author = "Nguyen, Minh Thuan and
Tran, Khanh Tung and
Nguyen, Nhu Van and
Vu, Xuan-Son",
editor = "Wang, Mingxuan and
Zitouni, Imed",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-industry.70",
doi = "10.18653/v1/2023.emnlp-industry.70",
pages = "754--764",
abstract = "Large language models (LLMs) and their applications in low-resource languages (such as in Vietnamese) are limited due to lack of training data and benchmarking datasets. This paper introduces a practical real-world implementation of a question answering system for Vietnamese, called ViGPTQA, leveraging the power of LLM. Since there is no effective LLM in Vietnamese to date, we also propose, evaluate, and open-source an instruction-tuned LLM for Vietnamese, named ViGPT. ViGPT demonstrates exceptional performances, especially on real-world scenarios. We curate a new set of benchmark datasets that encompass both AI and human-generated data, providing a comprehensive evaluation framework for Vietnamese LLMs. By achieving state-of-the-art results and approaching other multilingual LLMs, our instruction-tuned LLM underscores the need for dedicated Vietnamese-specific LLMs. Our open-source model supports customized and privacy-fulfilled Vietnamese language processing systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2023-vigptqa">
<titleInfo>
<title>ViGPTQA - State-of-the-Art LLMs for Vietnamese Question Answering: System Overview, Core Models Training, and Evaluations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="given">Thuan</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khanh</namePart>
<namePart type="given">Tung</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nhu</namePart>
<namePart type="given">Van</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan-Son</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) and their applications in low-resource languages (such as in Vietnamese) are limited due to lack of training data and benchmarking datasets. This paper introduces a practical real-world implementation of a question answering system for Vietnamese, called ViGPTQA, leveraging the power of LLM. Since there is no effective LLM in Vietnamese to date, we also propose, evaluate, and open-source an instruction-tuned LLM for Vietnamese, named ViGPT. ViGPT demonstrates exceptional performances, especially on real-world scenarios. We curate a new set of benchmark datasets that encompass both AI and human-generated data, providing a comprehensive evaluation framework for Vietnamese LLMs. By achieving state-of-the-art results and approaching other multilingual LLMs, our instruction-tuned LLM underscores the need for dedicated Vietnamese-specific LLMs. Our open-source model supports customized and privacy-fulfilled Vietnamese language processing systems.</abstract>
<identifier type="citekey">nguyen-etal-2023-vigptqa</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-industry.70</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-industry.70</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>754</start>
<end>764</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ViGPTQA - State-of-the-Art LLMs for Vietnamese Question Answering: System Overview, Core Models Training, and Evaluations
%A Nguyen, Minh Thuan
%A Tran, Khanh Tung
%A Nguyen, Nhu Van
%A Vu, Xuan-Son
%Y Wang, Mingxuan
%Y Zitouni, Imed
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F nguyen-etal-2023-vigptqa
%X Large language models (LLMs) and their applications in low-resource languages (such as in Vietnamese) are limited due to lack of training data and benchmarking datasets. This paper introduces a practical real-world implementation of a question answering system for Vietnamese, called ViGPTQA, leveraging the power of LLM. Since there is no effective LLM in Vietnamese to date, we also propose, evaluate, and open-source an instruction-tuned LLM for Vietnamese, named ViGPT. ViGPT demonstrates exceptional performances, especially on real-world scenarios. We curate a new set of benchmark datasets that encompass both AI and human-generated data, providing a comprehensive evaluation framework for Vietnamese LLMs. By achieving state-of-the-art results and approaching other multilingual LLMs, our instruction-tuned LLM underscores the need for dedicated Vietnamese-specific LLMs. Our open-source model supports customized and privacy-fulfilled Vietnamese language processing systems.
%R 10.18653/v1/2023.emnlp-industry.70
%U https://aclanthology.org/2023.emnlp-industry.70
%U https://doi.org/10.18653/v1/2023.emnlp-industry.70
%P 754-764
Markdown (Informal)
[ViGPTQA - State-of-the-Art LLMs for Vietnamese Question Answering: System Overview, Core Models Training, and Evaluations](https://aclanthology.org/2023.emnlp-industry.70) (Nguyen et al., EMNLP 2023)
ACL