Skip to content
CaMLSysUniversity of Cambridge
Home People Publications Projects Contact

← All publications

Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?

  • Zexi LiUniversity of CambridgeZhejiang University
  • Xiangzhu WangZhejiang University
  • William F. ShenUniversity of Cambridge
  • Meghdad KurmanjiUniversity of Cambridge
  • Xinchi QiuUniversity of Cambridge
  • Dongqi CaiUniversity of Cambridge
  • Chao WuZhejiang University
  • Nicholas D. LaneUniversity of Cambridge

AAAI Conference on Artificial Intelligence, 2026 · AI Alignment Track

Abstract

Large language Model (LLM) unlearning, i.e., selectively removing information from LLMs, is vital for responsible model deployment. Differently, LLM knowledge editing aims to modify LLM knowledge instead of removing it. Though editing and unlearning seem to be two distinct tasks, we find there is a tight connection between them. In this paper, we conceptualize unlearning as a special case of editing where information is modified to a refusal or “empty set” response, signifying its removal. This paper thus investigates if knowledge editing techniques are strong baselines for LLM unlearning. We evaluate state-of-the-art (SOTA) editing methods (e.g., ROME, MEMIT, GRACE, WISE, and AlphaEdit) against existing unlearning approaches on pretrained and finetuned knowledge. Results show certain editing methods, notably WISE and AlphaEdit, are effective unlearning baselines, especially for pretrained knowledge, and excel in generating human-aligned refusal answers. To better adapt editing methods for unlearning applications, we propose practical recipes including self-improvement and query merging. The former leverages the LLM’s own in-context learning ability to craft a more human-aligned unlearning target, and the latter enables ROME and MEMIT to perform well in unlearning longer sample sequences. We advocate for the unlearning community to adopt SOTA editing methods as baselines and explore unlearning from an editing perspective for more holistic LLM memory control.

Materials

  • PDF
BibTeX
@inproceedings{li2026editingasunlearning,
  title = {{Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?}},
  author = {Li, Zexi and Wang, Xiangzhu and Shen, William F. and Kurmanji, Meghdad and Qiu, Xinchi and Cai, Dongqi and Wu, Chao and Lane, Nicholas D.},
  year = {2026},
  booktitle = {AAAI Conference on Artificial Intelligence}
}
Cambridge Machine Learning Systems Group
Department of Computer Science and Technology
University of Cambridge
ContactGitHub