@inproceedings{chatzikyriakidis-natsina-2026-llms-got,
    title = "{LLM}s Got Rhyme? Hybrid Phonological Filtering for {G}reek Poetry Rhyme Detection and Generation",
    author = "Chatzikyriakidis, Stergios  and
      Natsina, Anastasia",
    editor = "Alves, Diego  and
      Bizzoni, Yuri  and
      Degaetano-Ortlieb, Stefania  and
      Kazantseva, Anna  and
      Pagel, Janis  and
      Szpakowicz, Stan",
    booktitle = "Proceedings of the 10th Joint {SIGHUM} Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.latechclfl-1.9/",
    pages = "87--101",
    ISBN = "979-8-89176-373-9",
    abstract = "Large Language Models (LLMs), even though exhibiting multiple capabilities on many NLP tasks, struggle with phonologically-grounded phenomena like rhyme detection and generation. When one moves to lower-resource languages such as Modern Greek, this is even more evident. In this paper, we present a hybrid neural-symbolic system that combines LLMs with deterministic phonological algorithms to achieve accurate rhyme identification and generation. We implement a comprehensive taxonomy of Greek rhyme types and employ an agentic generation pipeline with phonological verification. We use multiple prompting strategies (zero-shot, few-shot, Chain-of-Thought, and RAG-augmented) across several LLMs including Claude 3.7 and 4.5, GPT-4o, Gemini 2.0 and open-weight models like Llama 3.1 8B and 70B and Mistral Large. Results reveal a significant reasoning gap: while native-like models (Claude 3.7) perform intuitively (40{\textbackslash}{\%} accuracy in identification), reasoning-heavy models (Claude 4.5) achieve state-of-the-art performance (54{\textbackslash}{\%}) only when prompted with Chain-of-Thought. Most critically, pure LLM generation fails significantly (under 4{\textbackslash}{\%} valid poems), while our hybrid verification loop restores performance to 73.1{\textbackslash}{\%}. Along with the system presented, we further release a corpus of 40,000+ rhymes, derived from the {\textbackslash}textit{\{}Anemoskala{\}} and {\textbackslash}textit{\{}Interwar Poetry{\}} corpora, to support future research."
}