@inproceedings{xiao-etal-2026-representation,
    title = "Representation-Guided Parameter-Efficient {LLM} Unlearning",
    author = "Xiao, Zeguan  and
      Mo, Lang  and
      Chen, Yun  and
      Yang, Lei  and
      Zhao, Jiehui  and
      Yang, Lili  and
      Chen, Guanhua",
    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.717/",
    pages = "14602--14616",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Models (LLMs) often memorize sensitive or harmful information, necessitating effective machine unlearning techniques. While existing parameter-efficient unlearning methods have shown promise, they still struggle with the forget-retain trade-off. This can be attributed to their reliance on parameter importance metrics to identify parameters that are important exclusively for forget set, which is fundamentally limited by the superposition phenomenon. Due to the polysemantic nature of LLMs parameters, such an importance metric may struggle to disentangle parameters associated with forget and retain sets. In this work, we propose Representation-Guided Low-rank Unlearning (ReGLU), a novel approach that leverages the geometric properties of representation spaces to achieve robust and precise unlearning. First, we develop a representation-guided initialization for LoRA that identifies the optimal subspace for selective forgetting. Second, we introduce a regularization loss that constrains the outputs of the LoRA update to lie in the orthogonal complement of the retain set{'}s representation subspace, thereby minimizing interference with the model{'}s performance on the retain set. We evaluate ReGLU on the TOFU and WMDP benchmarks across multiple models. Our results demonstrate that ReGLU consistently outperforms state-of-the-art baselines, achieving superior unlearning quality while maintaining higher model utility."
}