@inproceedings{wen-etal-2025-lock,
    title = "Lock on Target! Precision Unlearning via Directional Control",
    author = "Wen, Yuntao  and
      Feng, Ruixiang  and
      Guo, Feng  and
      Wang, Yifan  and
      Le, Ran  and
      Song, Yang  and
      Gao, Shen  and
      Shang, Shuo",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1021/",
    doi = "10.18653/v1/2025.findings-emnlp.1021",
    pages = "18782--18794",
    ISBN = "979-8-89176-335-7",
    abstract = "The unlearning method aims at effectively removing harmful, sensitive, or outdated knowledge without costly retraining the model. However, existing methods suffer from two critical limitations: (1) collateral forgetting, where erasing target data inadvertently removes related but desirable knowledge, and (2) generality forgetting, where aggressive unlearning degrades the model{'}s general capabilities. To address these challenges, we propose DirectiOn Guide unlEarning (DOGE), a novel method that enables precise knowledge erasure by identifying and leveraging a targeted ``unlearning direction'' in the model{'}s parameter space. DOGE first extracts this direction through differential analysis of representations for forgotten and retained samples, pinpointing the exact subspace associated with unwanted knowledge. It then selectively applies updates along this direction, ensuring minimal interference with retained information and general model performance. Experiments across multiple benchmarks demonstrate that Doge achieves state-of-the-art unlearning precision while preserving both related knowledge and general capabilities."
}