@inproceedings{chatzikyriakidis-natsina-2025-poetry,
    title = "Poetry in {RAG}s: {M}odern {G}reek interwar poetry generation using {RAG} and contrastive training",
    author = "Chatzikyriakidis, Stergios  and
      Natsina, Anastasia",
    editor = {H{\"a}m{\"a}l{\"a}inen, Mika  and
      {\"O}hman, Emily  and
      Bizzoni, Yuri  and
      Miyagawa, So  and
      Alnajjar, Khalid},
    booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
    month = may,
    year = "2025",
    address = "Albuquerque, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.nlp4dh-1.22/",
    pages = "257--264",
    ISBN = "979-8-89176-234-3",
    abstract = "In this paper, we discuss Modern Greek poetry generation in the style of lesser known Greek poets of the interwar period. The paper proposes the use of Retrieval-Augmented Generation (RAG) to automatically generate poetry using Large Language Models (LLMs). A corpus of Greek interwar poetry is used and prompts exemplifying the poet`s style with respect to a theme are created. These are then fed to an LLM. The results are compared to pure LLM generation and expert evaluators score poems across a number of parameters. Objective metrics such as Vocabulary Density, Average words per Sentence and Readability Index are also used to assess the performance of the models. RAG-assisted models show potential in enhancing poetry generation across a number of parameters. Base LLM models appear quite consistent across a number of categories, while the RAG model that is furthermore contrastive shows the worst performance of the three."
}