@inproceedings{ondrejova-suppa-2024-llms,
    title = "Can {LLM}s Handle Low-Resource Dialects? A Case Study on Translation and Common Sense Reasoning in {\v{S}}ari{\v{s}}",
    author = "Ondrejov{\'a}, Vikt{\'o}ria  and
      {\v{S}}uppa, Marek",
    editor = {Scherrer, Yves  and
      Jauhiainen, Tommi  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Zampieri, Marcos  and
      Nakov, Preslav  and
      Tiedemann, J{\"o}rg},
    booktitle = "Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.vardial-1.11/",
    doi = "10.18653/v1/2024.vardial-1.11",
    pages = "130--139",
    abstract = "While Large Language Models (LLMs) have demonstrated considerable potential in advancing natural language processing in dialect-specific contexts, their effectiveness in these settings has yet to be thoroughly assessed. This study introduces a case study on {\v{S}}ari{\v{s}}, a dialect of Slovak, which is itself a language with fewer resources, focusing on Machine Translation and Common Sense Reasoning tasks. We employ LLMs in a zero-shot configuration and for data augmentation to refine Slovak-{\v{S}}ari{\v{s}} and {\v{S}}ari{\v{s}}-Slovak translation models. The accuracy of these models is then manually verified by native speakers. Additionally, we introduce {\v{S}}ari{\v{s}}COPA, a new dataset for causal common sense reasoning, which, alongside SlovakCOPA, serves to evaluate LLM`s performance in a zero-shot framework. Our findings highlight LLM`s capabilities in processing low-resource dialects and suggest a viable approach for initiating dialect-specific translation models in such contexts."
}