@inproceedings{fukuda-etal-2025-building,
title = "Building {J}apanese Creativity Benchmarks and Applying them to Enhance {LLM} Creativity",
author = "Fukuda, So and
Ogawa, Hayato and
Horio, Kaito and
Kawahara, Daisuke and
Shibata, Tomohide",
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.69/",
doi = "10.18653/v1/2025.acl-srw.69",
pages = "939--957",
ISBN = "979-8-89176-254-1",
abstract = "To evaluate the creativity of large language models (LLMs) in Japanese, we construct three benchmarks: Japanese Creativity Questions (JCQ), Divergent Association Task (DAT), and Story Alteration Task (SAT). JCQ comprehensively evaluates creativity using LLMs. Meanwhile, DAT and SAT measure specific aspects of creative ability using embeddings. We also analyze correlations between JCQ and DAT, JCQ and SAT, and DAT and SAT. While JCQ provides comprehensive evaluation, it is relatively time and resource intensive. In contrast, DAT and SAT offer lower comprehensiveness but enable quick, low-cost assessment. Additionally, we investigate whether training with DAT contributes to enhancing LLM creativity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fukuda-etal-2025-building">
<titleInfo>
<title>Building Japanese Creativity Benchmarks and Applying them to Enhance LLM Creativity</title>
</titleInfo>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Fukuda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hayato</namePart>
<namePart type="family">Ogawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaito</namePart>
<namePart type="family">Horio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomohide</namePart>
<namePart type="family">Shibata</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>To evaluate the creativity of large language models (LLMs) in Japanese, we construct three benchmarks: Japanese Creativity Questions (JCQ), Divergent Association Task (DAT), and Story Alteration Task (SAT). JCQ comprehensively evaluates creativity using LLMs. Meanwhile, DAT and SAT measure specific aspects of creative ability using embeddings. We also analyze correlations between JCQ and DAT, JCQ and SAT, and DAT and SAT. While JCQ provides comprehensive evaluation, it is relatively time and resource intensive. In contrast, DAT and SAT offer lower comprehensiveness but enable quick, low-cost assessment. Additionally, we investigate whether training with DAT contributes to enhancing LLM creativity.</abstract>
<identifier type="citekey">fukuda-etal-2025-building</identifier>
<identifier type="doi">10.18653/v1/2025.acl-srw.69</identifier>
<location>
<url>https://aclanthology.org/2025.acl-srw.69/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>939</start>
<end>957</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building Japanese Creativity Benchmarks and Applying them to Enhance LLM Creativity
%A Fukuda, So
%A Ogawa, Hayato
%A Horio, Kaito
%A Kawahara, Daisuke
%A Shibata, Tomohide
%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 fukuda-etal-2025-building
%X To evaluate the creativity of large language models (LLMs) in Japanese, we construct three benchmarks: Japanese Creativity Questions (JCQ), Divergent Association Task (DAT), and Story Alteration Task (SAT). JCQ comprehensively evaluates creativity using LLMs. Meanwhile, DAT and SAT measure specific aspects of creative ability using embeddings. We also analyze correlations between JCQ and DAT, JCQ and SAT, and DAT and SAT. While JCQ provides comprehensive evaluation, it is relatively time and resource intensive. In contrast, DAT and SAT offer lower comprehensiveness but enable quick, low-cost assessment. Additionally, we investigate whether training with DAT contributes to enhancing LLM creativity.
%R 10.18653/v1/2025.acl-srw.69
%U https://aclanthology.org/2025.acl-srw.69/
%U https://doi.org/10.18653/v1/2025.acl-srw.69
%P 939-957
Markdown (Informal)
[Building Japanese Creativity Benchmarks and Applying them to Enhance LLM Creativity](https://aclanthology.org/2025.acl-srw.69/) (Fukuda et al., ACL 2025)
ACL