@inproceedings{heierli-etal-2025-evaluating,
    title = "Evaluating {LLM} Capabilities in Low-Resource Contexts: A Case Study of {P}ersian Linguistic and Cultural Tasks",
    author = "Heierli, Jasmin  and
      Ganjineh, Rebecca Bahar  and
      Gavagnin, Elena",
    editor = "Estevanell-Valladares, Ernesto Luis  and
      Picazo-Izquierdo, Alicia  and
      Ranasinghe, Tharindu  and
      Mikaberidze, Besik  and
      Ostermann, Simon  and
      Gurgurov, Daniil  and
      Mueller, Philipp  and
      Borg, Claudia  and
      {\v{S}}imko, Mari{\'a}n",
    booktitle = "Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages",
    month = sep,
    year = "2025",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd., Shoumen, Bulgaria",
    url = "https://preview.aclanthology.org/corrections-2026-01/2025.lowresnlp-1.12/",
    pages = "111--120",
    abstract = "We evaluate four representative large language models, namely GPT-4o, Gemini, Llama, and DeepSeek on on a suite of linguistic and cultural tasks in Persian, covering grammar, paraphrasing, inference, translation, factual recall, analogical reasoning, and a Hofstede-based cultural probe under direct and role-based prompts. Our findings reveal consistent performance declines, alongside systematic misalignment with Iranian cultural norms. Role-based prompting yields modest improvements but does not fully restore cultural fidelity. We conclude that advancing truly multilingual models demands richer Persian resources, targeted adaptation, and evaluation frameworks that jointly assess fluency and cultural alignment."
}