@inproceedings{peng-etal-2026-accelerating,
    title = "Accelerating {LLM} Fine-Tuning via Embedding Knowledge Transfer",
    author = "Peng, Meishu  and
      Zhang, Ziyue  and
      Zhang, Yi  and
      Wang, Pengyang  and
      Yuan, Zixuan  and
      Zhang, Denghui",
    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.5/",
    pages = "90--107",
    ISBN = "979-8-89176-395-1",
    abstract = "Incorporating Large Language Models (LLMs) for downstream tasks has recently garnered considerable attention, where fine-tuning plays a key role in LLMs' adaptation. These LLMs, often consisting of billions of parameters, require vast amounts of computational resources when customizing them for new tasks. To mitigate this, researchers have proposed the parameter-efficient fine-tuning (PEFT) as a practical solution by adjusting fewer parameters of a pre-trained LLM. However, these methods heavily rely on their own structural modifications that fail to establish an efficient knowledge-sharing mechanism to distill rich knowledge from other expert models, which may lead to inefficient fine-tuning. In this paper, we propose Pen2Sword, a lightweight fine-tuning framework for domain adaptation which efficiently transfers knowledge from a small expert model to a target large model via embedding layers, significantly enhancing the fine-tuning efficiency of large models. Specifically, we first selects optimal expert models via a preserving function, then facilitates knowledge transfer through vocabulary alignment and embedding expansion, and finally accelerates domain adaptation with a fast fine-tuning paradigm. Extensive empirical evaluations across multiple domains demonstrate that our Pen2Sword framework consistently accelerates domain-specific fine-tuning, improves model performance (e.g., +13.6{\%} in code and +20.1{\%} in math), and remains robust across diverse model families and PEFT methods. The codes and data are available at https://github.com/pengmeishu/Pen2Sword."
}