@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://preview.aclanthology.org/landing_page/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."
}