@inproceedings{yi-etal-2026-group,
    title = "Group-Merger: A {L}o{RA}-based Framework for Multilingual Continual Learning",
    author = "yi, Weijian  and
      Li, Hongliang  and
      Xu, Jinan",
    editor = "Huang, Kaiyu  and
      Mo, Fengran  and
      Chen, Pinzhen  and
      Jiang, Meng",
    booktitle = "Proceedings of the 1st Workshop on Multilinguality in the Era of Large Language Models ({M}e{LLM} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.mellm-1.30/",
    pages = "308--316",
    ISBN = "979-8-89176-430-9",
    abstract = "Multilingual continual learning (MCL) is crucial for enabling language models to adapt across diverse linguistic environments while retaining knowledge over time. Existing parameter isolation methods allocate language-specific modules but fail to leverage cross-lingual transfer, leading to inefficient parameter growth and poor generalization. Model merging based approaches suffer from severe performance degradation as the number of language-specific tasks increases, due to interference between linguistic and task-specific knowledge. To address these challenges, we propose \textbf{Group-Merger}, a framework that employs group-wise merging to balance parameter efficiency and continual learning performance. Our framework mitigates catastrophic forgetting across languages while enabling knowledge transfer. Extensive experiments on multilingual evaluation benchmarks demonstrate superior performance compared to existing methods."
}