作者位次 #4/8ACL 2026Findings· Findings of ACL
AGT AO : Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality
Pengyu Li · Lingling Zhang · Zhitao Gao · Yanrui Wu · Yuxuan Dong · Huan Liu · Bifan Wei · an Jiaotong University)
摘要
While Large Language Models (LLMs) have achieved remarkable capabilities, they unintentionally memorize sensitive data, posing critical privacy and security risks.Machine unlearning is pivotal for mitigating these risks, yet existing paradigms face a fundamental dilemma: aggressive unlearning oft...