@article{chatzikyriakidis-etal-2026-grdd,
    title = "{GRDD}+: An Extended {G}reek Dialectal Dataset with Cross-Architecture Fine-tuning Evaluation",
    author = "Chatzikyriakidis, Stergios  and
      Papadakis, Dimitri{o}s  and
      Papaioannou, Sevasti Ioanna  and
      Psaltaki, Erofili",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.245/",
    pages = "3138--3146",
    abstract = "We present an extended Greek Dialectal Dataset (GRDD+) that complements the existing GRDD dataset with more data from Cretan, Cypriot, Pontic and Northern Greek, while we add six new varieties: Greco-Corsican, Griko (Southern Italian Greek), Maniot, Heptanesian, Tsakonian, and Katharevusa Greek. The result is a dataset with total size 6,374,939 words and 10 varieties. This is the first dataset with such variation and size to date. We conduct a number of fine-tuning experiments to see the effect of good quality dialectal data on a number of LLMs. We fine-tune three model architectures (Llama-3-8B, Llama-3.1-8B, Krikri-8B) and compare the results to frontier models (Claude-3.7-Sonnet, Gemini-2.5, ChatGPT-5)."
}