@inproceedings{nanomi-arachchige-etal-2025-toponym,
    title = "Toponym Resolution: Will Prompt Engineering Change Expectations?",
    author = "Nanomi Arachchige, Isuri Anuradha  and
      Sumanathilaka, Deshan Koshala  and
      Mitkov, Ruslan  and
      Rayson, Paul",
    editor = "Angelova, Galia  and
      Kunilovskaya, Maria  and
      Escribe, Marie  and
      Mitkov, Ruslan",
    booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
    month = sep,
    year = "2025",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd., Shoumen, Bulgaria",
    url = "https://preview.aclanthology.org/just-dir/2025.ranlp-1.11/",
    pages = "95--104",
    abstract = "Deep Learning and, more recently, Large Language Models(LLMs) have revolutionised the field of artificial intelligence and have been successfully employed in many disciplines, capturing widespread attention and enthusiasm. Many previous studies have established that domain-specific Deep Learning models competitively perform with the general-purpose LLMs. However, a suitable prompt which provides direct instructions and background information is expected to yield improved results. The present study, which focuses on Large Language Models for Toponym Resolution, shows that effective Prompt Engineering techniques without fine-tuning or pre-training approaches enable LLMs to surpass Deep Learning models, which is contrary to the initial expectations. After a comparison of open-source and proprietary LLMs and different prompt engineering techniques, the GPT-4o model performs best compared to the other open-source LLMs."
}