@inproceedings{holmstrom-etal-2023-bridging,
    title = "Bridging the Resource Gap: Exploring the Efficacy of {E}nglish and Multilingual {LLM}s for {S}wedish",
    author = {Holmstr{\"o}m, Oskar  and
      Kunz, Jenny  and
      Kuhlmann, Marco},
    editor = "Ilinykh, Nikolai  and
      Morger, Felix  and
      Dann{\'e}lls, Dana  and
      Dobnik, Simon  and
      Megyesi, Be{\'a}ta  and
      Nivre, Joakim",
    booktitle = "Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)",
    month = may,
    year = "2023",
    address = "T{\'o}rshavn, the Faroe Islands",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.resourceful-1.13/",
    pages = "92--110",
    abstract = "Large language models (LLMs) have substantially improved natural language processing (NLP) performance, but training these models from scratch is resource-intensive and challenging for smaller languages. With this paper, we want to initiate a discussion on the necessity of language-specific pre-training of LLMs.We propose how the {\textquotedblleft}one model-many models{\textquotedblright} conceptual framework for task transfer can be applied to language transfer and explore this approach by evaluating the performance of non-Swedish monolingual and multilingual models' performance on tasks in Swedish.Our findings demonstrate that LLMs exposed to limited Swedish during training can be highly capable and transfer competencies from English off-the-shelf, including emergent abilities such as mathematical reasoning, while at the same time showing distinct culturally adapted behaviour. Our results suggest that there are resourceful alternatives to language-specific pre-training when creating useful LLMs for small languages."
}