@inproceedings{zheng-etal-2025-exploring,
    title = "Exploring the Application of 7{B} {LLM}s for Named Entity Recognition in {C}hinese Ancient Texts",
    author = "Zheng, Chenrui  and
      Zhu, Yicheng  and
      Bi, Han",
    editor = "Anderson, Adam  and
      Gordin, Shai  and
      Li, Bin  and
      Liu, Yudong  and
      Passarotti, Marco C.  and
      Sprugnoli, Rachele",
    booktitle = "Proceedings of the Second Workshop on Ancient Language Processing",
    month = may,
    year = "2025",
    address = "The Albuquerque Convention Center, Laguna",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2025.alp-1.18/",
    doi = "10.18653/v1/2025.alp-1.18",
    pages = "150--155",
    ISBN = "979-8-89176-235-0",
    abstract = "This paper explores the application of fine-tuning methods based on 7B large language models (LLMs) for named entity recognition (NER) tasks in Chinese ancient texts. Targeting the complex semantics and domain-specific characteristics of ancient texts, particularly in Traditional Chinese Medicine (TCM) texts, we propose a comprehensive fine-tuning and pre-training strategy. By introducing multi-task learning, domain-specific pre-training, and efficient fine-tuning techniques based on LoRA, we achieved significant performance improvements in ancient text NER tasks. Experimental results show that the pre-trained and fine-tuned 7B model achieved an F1 score of 0.93, significantly outperforming general-purpose large language models."
}