@inproceedings{schlenker-etal-2025-unseen,
    title = "Only for the Unseen Languages, Say the Llamas: On the Efficacy of Language Adapters for Cross-lingual Transfer in {E}nglish-centric {LLM}s",
    author = {Schlenker, Julian  and
      Kunz, Jenny  and
      Anikina, Tatiana  and
      Neumann, G{\"u}nter  and
      Ostermann, Simon},
    editor = "Zhao, Jin  and
      Wang, Mingyang  and
      Liu, Zhu",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-srw.62/",
    pages = "849--871",
    ISBN = "979-8-89176-254-1",
    abstract = "Most state-of-the-art large language models (LLMs) are trained mainly on English data, limiting their effectiveness on non-English, especially low-resource, languages. This study investigates whether language adapters can facilitate cross-lingual transfer in English-centric LLMs. We train language adapters for 13 languages using Llama 2 (7B) and Llama 3.1 (8B) as base models, and evaluate their effectiveness on two downstream tasks (MLQA and SIB-200) using either task adapters or in-context learning. Our results reveal that language adapters improve performance for languages not seen during pretraining, but provide negligible benefit for seen languages. These findings highlight the limitations of language adapters as a general solution for multilingual adaptation in English-centric LLMs."
}