@inproceedings{choi-etal-2026-kuest,
title = "{KUEST}: {K}orean game Usage Evaluation Suite for {LLM} Translation",
author = "Choi, Minjoo and
Jung, Jaejun and
Han, Gunwoo and
Kim, Junhyeop and
Yoon, Yiji and
Kim, Hyemi and
Cho, Yeonseo and
Jang, Jinwoo",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wmt-main.86/",
pages = "1484--1505",
ISBN = "979-8-89176-474-3",
abstract = "Despite the growing demand for multilingual game localization, systematic evaluation frameworks for game translation constraints remain largely unexplored. As part of the WMT26 Test Suite Track, we propose KUEST, a test suite comprising 1,796 English-to-Korean segments across four core categories, and evaluate 27 submitted systems. Experimental results demonstrate that standard metrics obscure true model capabilities (e.g., the overall 1st-place system dropping to 15th in creative translation). Furthermore, we reveal residual capability fragmentation{---}category-specific variance that survives the shared general-competence factor and inverts top-tier rankings{---}and observe a ``prompt gap'' where context metadata degrades performance. As such, KUEST serves not only as a test suite but also as an evaluation framework that multi-dimensionally dissects domain-specific translation blind spots hidden behind single composite scores. The dataset is available at https://huggingface.co/datasets/JudyChoi/KUEST."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choi-etal-2026-kuest">
<titleInfo>
<title>KUEST: Korean game Usage Evaluation Suite for LLM Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minjoo</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaejun</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gunwoo</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhyeop</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiji</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyemi</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeonseo</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinwoo</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eleventh Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-474-3</identifier>
</relatedItem>
<abstract>Despite the growing demand for multilingual game localization, systematic evaluation frameworks for game translation constraints remain largely unexplored. As part of the WMT26 Test Suite Track, we propose KUEST, a test suite comprising 1,796 English-to-Korean segments across four core categories, and evaluate 27 submitted systems. Experimental results demonstrate that standard metrics obscure true model capabilities (e.g., the overall 1st-place system dropping to 15th in creative translation). Furthermore, we reveal residual capability fragmentation—category-specific variance that survives the shared general-competence factor and inverts top-tier rankings—and observe a “prompt gap” where context metadata degrades performance. As such, KUEST serves not only as a test suite but also as an evaluation framework that multi-dimensionally dissects domain-specific translation blind spots hidden behind single composite scores. The dataset is available at https://huggingface.co/datasets/JudyChoi/KUEST.</abstract>
<identifier type="citekey">choi-etal-2026-kuest</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.86/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1484</start>
<end>1505</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KUEST: Korean game Usage Evaluation Suite for LLM Translation
%A Choi, Minjoo
%A Jung, Jaejun
%A Han, Gunwoo
%A Kim, Junhyeop
%A Yoon, Yiji
%A Kim, Hyemi
%A Cho, Yeonseo
%A Jang, Jinwoo
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F choi-etal-2026-kuest
%X Despite the growing demand for multilingual game localization, systematic evaluation frameworks for game translation constraints remain largely unexplored. As part of the WMT26 Test Suite Track, we propose KUEST, a test suite comprising 1,796 English-to-Korean segments across four core categories, and evaluate 27 submitted systems. Experimental results demonstrate that standard metrics obscure true model capabilities (e.g., the overall 1st-place system dropping to 15th in creative translation). Furthermore, we reveal residual capability fragmentation—category-specific variance that survives the shared general-competence factor and inverts top-tier rankings—and observe a “prompt gap” where context metadata degrades performance. As such, KUEST serves not only as a test suite but also as an evaluation framework that multi-dimensionally dissects domain-specific translation blind spots hidden behind single composite scores. The dataset is available at https://huggingface.co/datasets/JudyChoi/KUEST.
%U https://aclanthology.org/2026.wmt-main.86/
%P 1484-1505
Markdown (Informal)
[KUEST: Korean game Usage Evaluation Suite for LLM Translation](https://aclanthology.org/2026.wmt-main.86/) (Choi et al., WMT 2026)
ACL
- Minjoo Choi, Jaejun Jung, Gunwoo Han, Junhyeop Kim, Yiji Yoon, Hyemi Kim, Yeonseo Cho, and Jinwoo Jang. 2026. KUEST: Korean game Usage Evaluation Suite for LLM Translation. In Proceedings of the Eleventh Conference on Machine Translation, pages 1484–1505, Budapest, Hungary. Association for Computational Linguistics.