Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning

Summary

Nullify is a training-free method for unlearning specific knowledge from LLMs at inference time, without weight updates. It applies steering vectors to redirect privacy-related activations away from memorized answers, while a null-space constraint keeps retained-query activations essentially unchanged. On TOFU and MUSE, it matches or surpasses established baselines in forget quality and achieves near-lossless preservation of model utility.