@inproceedings{jang-etal-2024-kit,
title = "{KIT}-19: A Comprehensive {K}orean Instruction Toolkit on 19 Tasks for Fine-Tuning {K}orean Large Language Models",
author = "Jang, Dongjun and
Byun, Sungjoo and
Jo, Hyemi and
Shin, Hyopil",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.853/",
pages = "9764--9776",
abstract = "Instruction Tuning on Large Language Models is an essential process for model to function well and achieve high performance in the specific tasks. Accordingly, in mainstream languages such as English, instruction-based datasets are being constructed and made publicly available. In the case of Korean, publicly available models and datasets all rely on using the output of ChatGPT or translating datasets built in English. In this paper, We introduce \textit{KIT-19} as an instruction dataset for the development of LLM in Korean. \textit{KIT-19} is a dataset created in an instruction format, comprising 19 existing open-source datasets for Korean NLP tasks. In this paper, we train a Korean Pretrained LLM using \textit{KIT-19} to demonstrate its effectiveness. The experimental results show that the model trained on \textit{KIT-19} significantly outperforms existing Korean LLMs. Based on the its quality and empirical results, this paper proposes that \textit{KIT-19} has the potential to make a substantial contribution to the future improvement of Korean LLMs' performance."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jang-etal-2024-kit">
<titleInfo>
<title>KIT-19: A Comprehensive Korean Instruction Toolkit on 19 Tasks for Fine-Tuning Korean Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongjun</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungjoo</namePart>
<namePart type="family">Byun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyemi</namePart>
<namePart type="family">Jo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyopil</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Instruction Tuning on Large Language Models is an essential process for model to function well and achieve high performance in the specific tasks. Accordingly, in mainstream languages such as English, instruction-based datasets are being constructed and made publicly available. In the case of Korean, publicly available models and datasets all rely on using the output of ChatGPT or translating datasets built in English. In this paper, We introduce KIT-19 as an instruction dataset for the development of LLM in Korean. KIT-19 is a dataset created in an instruction format, comprising 19 existing open-source datasets for Korean NLP tasks. In this paper, we train a Korean Pretrained LLM using KIT-19 to demonstrate its effectiveness. The experimental results show that the model trained on KIT-19 significantly outperforms existing Korean LLMs. Based on the its quality and empirical results, this paper proposes that KIT-19 has the potential to make a substantial contribution to the future improvement of Korean LLMs’ performance.</abstract>
<identifier type="citekey">jang-etal-2024-kit</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.853/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9764</start>
<end>9776</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KIT-19: A Comprehensive Korean Instruction Toolkit on 19 Tasks for Fine-Tuning Korean Large Language Models
%A Jang, Dongjun
%A Byun, Sungjoo
%A Jo, Hyemi
%A Shin, Hyopil
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F jang-etal-2024-kit
%X Instruction Tuning on Large Language Models is an essential process for model to function well and achieve high performance in the specific tasks. Accordingly, in mainstream languages such as English, instruction-based datasets are being constructed and made publicly available. In the case of Korean, publicly available models and datasets all rely on using the output of ChatGPT or translating datasets built in English. In this paper, We introduce KIT-19 as an instruction dataset for the development of LLM in Korean. KIT-19 is a dataset created in an instruction format, comprising 19 existing open-source datasets for Korean NLP tasks. In this paper, we train a Korean Pretrained LLM using KIT-19 to demonstrate its effectiveness. The experimental results show that the model trained on KIT-19 significantly outperforms existing Korean LLMs. Based on the its quality and empirical results, this paper proposes that KIT-19 has the potential to make a substantial contribution to the future improvement of Korean LLMs’ performance.
%U https://aclanthology.org/2024.lrec-main.853/
%P 9764-9776
Markdown (Informal)
[KIT-19: A Comprehensive Korean Instruction Toolkit on 19 Tasks for Fine-Tuning Korean Large Language Models](https://aclanthology.org/2024.lrec-main.853/) (Jang et al., LREC-COLING 2024)
ACL