Test-Time Unlearning via Sparse Autoencoder
This work proposes ARIA (autoencoder-gated inference-time unlearning), a test-time unlearning method that leaves model weights intact and gates access to unwanted knowledge only when generation enters a forget-related state and introduces three post-unlearning adversarial attacks targeting weight-space and decoding-spa...
Ping-Zhi Li, Jinhao Duan, Vaishnav Tadiparthi et al.
· 0 citations