@inproceedings{yu-etal-2025-making,
title = "Making Sense of {K}orean Sentences: A Comprehensive Evaluation of {LLM}s through {K}o{SE}nd Dataset",
author = "Yu, Seunguk and
Kim, Kyeonghyun and
Yun, JungMin and
Kim, YoungBin",
editor = "Zhao, Jin and
Wang, Mingyang and
Liu, Zhu",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-srw.29/",
doi = "10.18653/v1/2025.acl-srw.29",
pages = "455--469",
ISBN = "979-8-89176-254-1",
abstract = "Although LLMs have made significant progress in various languages, there are still concerns about their effectiveness with low-resource agglutinative languages compared to languages such as English. In this study, we focused on Korean, a language known for its complex sentence endings, and evaluated LLMs on this challenging aspect. We introduce the Korean Sentence Endings (KoSEnd) dataset, which includes 3,000 sentences, each annotated for the naturalness of 15 sentence ending forms. These were collected from diverse sources to cover a range of contexts. We evaluated 11 LLMs to assess their understanding of Korean sentence endings, analyzing them based on parameter count and prediction consistency. Notably, we found that informing models about the possibility of missing sentence endings improved performance, highlighting the impact of explicitly considering certain linguistic features."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2025-making">
<titleInfo>
<title>Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seunguk</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyeonghyun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">JungMin</namePart>
<namePart type="family">Yun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">YoungBin</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingyang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-254-1</identifier>
</relatedItem>
<abstract>Although LLMs have made significant progress in various languages, there are still concerns about their effectiveness with low-resource agglutinative languages compared to languages such as English. In this study, we focused on Korean, a language known for its complex sentence endings, and evaluated LLMs on this challenging aspect. We introduce the Korean Sentence Endings (KoSEnd) dataset, which includes 3,000 sentences, each annotated for the naturalness of 15 sentence ending forms. These were collected from diverse sources to cover a range of contexts. We evaluated 11 LLMs to assess their understanding of Korean sentence endings, analyzing them based on parameter count and prediction consistency. Notably, we found that informing models about the possibility of missing sentence endings improved performance, highlighting the impact of explicitly considering certain linguistic features.</abstract>
<identifier type="citekey">yu-etal-2025-making</identifier>
<identifier type="doi">10.18653/v1/2025.acl-srw.29</identifier>
<location>
<url>https://aclanthology.org/2025.acl-srw.29/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>455</start>
<end>469</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset
%A Yu, Seunguk
%A Kim, Kyeonghyun
%A Yun, JungMin
%A Kim, YoungBin
%Y Zhao, Jin
%Y Wang, Mingyang
%Y Liu, Zhu
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-254-1
%F yu-etal-2025-making
%X Although LLMs have made significant progress in various languages, there are still concerns about their effectiveness with low-resource agglutinative languages compared to languages such as English. In this study, we focused on Korean, a language known for its complex sentence endings, and evaluated LLMs on this challenging aspect. We introduce the Korean Sentence Endings (KoSEnd) dataset, which includes 3,000 sentences, each annotated for the naturalness of 15 sentence ending forms. These were collected from diverse sources to cover a range of contexts. We evaluated 11 LLMs to assess their understanding of Korean sentence endings, analyzing them based on parameter count and prediction consistency. Notably, we found that informing models about the possibility of missing sentence endings improved performance, highlighting the impact of explicitly considering certain linguistic features.
%R 10.18653/v1/2025.acl-srw.29
%U https://aclanthology.org/2025.acl-srw.29/
%U https://doi.org/10.18653/v1/2025.acl-srw.29
%P 455-469
Markdown (Informal)
[Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset](https://aclanthology.org/2025.acl-srw.29/) (Yu et al., ACL 2025)
ACL