ResearchResearch paperLarge Language Models1 source · Oct 7, 2026

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

To address this, we propose Nullify, a training-free, non-destructive activation steering method for LLM unlearning.

Large Language Models (LLMs) inevitably internalize substantial amounts of sensitive or private information during pre-training, while LLM unlearning aims to selectively erase specific knowledge to prevent privacy leakage with minimal loss of model utility.
Nullify employs steering vectors during inference to redirect privacy-related activations away from their memorized answers, while satisfying a null-space constraint that leaves retained-query activations essentially unaffected to maintain utility.
Evaluations on TOFU and MUSE show that Nullify matches or surpasses established baselines in forget quality while achieving near-lossless preservation of model utility.
By avoiding weight updates entirely, Nullify serves as an efficient, plug-and-play inference-time intervention framework.

[1]Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning
arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 04:24 PM
To address this, we propose Nullify, a training-free, non-destructive activation steering method for LLM unlearning.
Large Language Models (LLMs) inevitably internalize substantial amounts of sensitive or private information during pre-training, while LLM unlearning aims to selectively erase specific knowledge to prevent privacy leakage with minimal loss of model utility.

Extractive summary: sentences quoted from the sources.

Before this