works on
activation steering 1inference-time methods 1large language models 1machine unlearning 1model privacy 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.LG2026

Inference-Time Machine Unlearning via Gated Activation Redirection

Vinícius Conte Turani, Otávio Parraga, João Vitor Boer Abitante +7

The paper proposes GUARD-IT, a gradient‑free method that modifies activations at inference time with input‑dependent rotations to erase specific data from large language models whi…