\textbf{AGT^{AO}}: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality

2 February 2026

Pengyu Li

Lingling Zhang

Zhitao Gao

Yanrui Wu

Yuxuan Dong

Huan Liu

Bifan Wei

Jun Liu

AAMLMURe-assign community

ArXiv (abs)PDFHTML

Papers citing "$\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality"