@inproceedings{ogawa-kawahara-2026-constructing,
    title = "Constructing a {J}apanese Rap Lyric Generation Model with {GRPO}",
    author = "Ogawa, Hayato  and
      Kawahara, Daisuke",
    editor = "T.Y.S.S., Santosh  and
      Rodriguez, Juan Diego  and
      de Gibert, Ona",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-srw.27/",
    pages = "340--351",
    ISBN = "979-8-89176-393-7",
    abstract = "Rap is a vocal style rooted in Hip-Hop culture, characterized by producing rhymes in synchrony with a rhythmic beat.This paper proposes a method for generating Japanese rap lyrics with a large language model (LLM) whose rhyming behavior is improved via reinforcement learning.We design a reward function that evaluates end rhymes between two generated bars and apply GRPO, a reinforcement-learning method, to encourage Japanese rhyming without using existing Japanese rap lyrics as training data.Experimental results show that, although output collapse is observed in some cases, GRPO increases the proportion of outputs that receive moderate or high human ratings on rhyme-related criteria."
}