@inproceedings{gutierrez-etal-2025-fsts,
    title = "{FST}s vs {ICL}: Generalisation in {LLM}s for an under-resourced language",
    author = "Gutierrez, Ximena  and
      Elizalde, Mikel Segura  and
      Mijangos, Victor",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.867/",
    doi = "10.18653/v1/2025.findings-emnlp.867",
    pages = "15998--16006",
    ISBN = "979-8-89176-335-7",
    abstract = "LLMs have been widely adopted to tackle many traditional NLP tasks. Their effectiveness remains uncertain in scenarios where pre-trained models have limited prior knowledge of a language. In this work, we examine LLMs' generalization in under-resourced settings through the task of orthographic normalization across Otomi language variants. We develop two approaches: a rule-based method using a finite-state transducer (FST) and an in-context learning (ICL) method that provides the model with string transduction examples. We compare the performance of FSTs and neural approaches in low-resource scenarios, providing insights into their potential and limitations. Our results show that while FSTs outperform LLMs in zero-shot settings, ICL enables LLMs to surpass FSTs, stressing the importance of combining linguistic expertise with machine learning in current approaches for low-resource scenarios."
}