作者位次 #5/6ACL 2026Findings· Findings of ACL
Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space
Xiang Zhang · Kun Wei · Xu Yang · Jiahua Li · Su Yan · Cheng Deng
摘要
As Large Language Models (LLMs) become increasingly prevalent, their security vulnerabilities have already drawn attention.Machine unlearning is introduced to seek to mitigate these risks by removing the influence of undesirable data. However, existing methods not only rely on the retained datase...