activation steering 1inference-time methods 1large language models 1machine unlearning 1model privacy 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.LG2026
Inference-Time Machine Unlearning via Gated Activation Redirection
VinÃcius 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…
cs.LG2026
Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning
Joana Pasquali, Ramiro N. Barros, Arthur S. Bianchessi +7
LoRA is widely adopted for continual fine-tuning of Large Language Models due to its parameter efficiency, modularity across tasks, and compatibility with replay strategies. Howeve…