@inproceedings{tran-etal-2026-disentangling,
    title = "Disentangling Continued Pre-Training: Attention-Driven Routing and Semantic Hub Preservation in Language Adaptation",
    author = "Tran, Khanh-Tung  and
      Tran, Vinh-Khanh  and
      O'Sullivan, Barry  and
      Nguyen, Hoang D.",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1218/",
    pages = "24335--24357",
    ISBN = "979-8-89176-395-1",
    abstract = "Continued Pre-Training (CPT) enables Large Language Models (LLMs) to acquire second-language capabilities, yet the underlying mechanisms remain poorly understood. In this work, we investigate how CPT adapts model representations across diverse language families and scripts, model sizes, and architectures. We find that second-language abilities emerge through a selective adaptation mechanism: task-solving capabilities are preserved in ``semantic hub'', while interface layers retarget to shifted token distributions. Layer-swapping experiments demonstrate that semantic understanding can be surgically transferred between base and CPT models with minimal loss (e.g., swapping 50{\%} of model parameters reduces performance by only 0.3{\%}). Furthermore, we establish that attention components route language adaptation: larger parameter changes than feedforward networks, correlate more strongly with language-specific neurons, and their surgical replacement substantially degrades performance. Overall, our work provides a mechanistic understanding of CPT, guiding future work on efficient strategies for language adaptation."
}