@inproceedings{zhang-etal-2026-balancing,
    title = "Balancing Knowledge Breadth and Task Depth for Effective Domain Adaptation Fine-Tuning",
    author = "Zhang, Mu  and
      Chu, Yuxiang  and
      Yu, Guangya  and
      Fan, Yongqi  and
      Zhang, Weiyan  and
      Hu, Hang  and
      Ruan, Tong  and
      Liu, Jingping",
    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.405/",
    pages = "8287--8304",
    ISBN = "979-8-89176-395-1",
    abstract = "Training large language models for domain adaptation poses a significant challenge in balancing the acquisition of domain knowledge with the retention of general abilities, often leading to catastrophic forgetting. While curriculum learning offers a promising direction, conventional methods typically rely on a single dimension of knowledge or task, which is insufficient to navigate the trade-off between knowledge breadth and task depth. In this paper, we propose a two-dimensional curriculum learning framework that coordinates model training along two orthogonal axes: the knowledge dimension and the task dimension. We first reconstruct the dataset by clustering instances according to their semantic similarity to general-domain data, and subsequently annotate them with a task hierarchy. Then, we design an integrated curriculum that develops from general to domain-specific knowledge clusters, and within each cluster, from lower- to higher-order cognitive tasks. Compared with the second-best method, our method improves accuracy on medical evaluations by 2.49{\%} and on financial evaluations by 1.2{\%}. Ablation and cross-domain experiments further demonstrate our method as a scalable and effective framework for structured domain adaptation in large language model fine-tuning. We have released the code in an anonymous repository at https://github.com/Melo-1017/Balancing-Knowledge-Breadth-and-Task-Depth."
}