@inproceedings{xie-etal-2024-efficient,
    title = "Efficient Continual Pre-training for Building Domain Specific Large Language Models",
    author = "Xie, Yong  and
      Aggarwal, Karan  and
      Ahmad, Aitzaz",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2024.findings-acl.606/",
    doi = "10.18653/v1/2024.findings-acl.606",
    pages = "10184--10201",
    abstract = "Large language models (LLMs) have demonstrated remarkable open-domain capabilities. LLMs tailored for a domain are typically trained entirely on domain corpus to excel at handling domain-specific tasks. In this work, we explore an alternative strategy of continual pre-training as a means to develop domain-specific LLMs over an existing open-domain LLM. We introduce \textit{FinPythia-6.9B}, developed through domain-adaptive continual pre-training on the financial domain.Continual pre-trained FinPythia showcases consistent improvements on financial tasks over the original foundational model. We further explore simple but effective data selection strategies for continual pre-training. Our data selection strategies outperform vanilla continual pre-training{'}s performance with just 10{\%} of corpus size and cost, without any degradation on open-domain standard tasks. Our work proposes an alternative solution to building domain-specific LLMs cost-effectively."
}