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

arXiv: https://arxiv.org/abs/2610.10655 · HTML: https://mlsanity.com/paper/2610.10655/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 5 of its 30 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 5 of 5)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [Towards Effective Evaluations and Comparisons for LLM Unlearning Methods](https://mlsanity.com/paper/2406.09179/) (2024)
- [GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection](https://mlsanity.com/paper/2505.13312/) (2025)

## Abstract (arXiv)

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. However, existing methods struggle to balance forget quality with utility, and typically incur substantial computational costs due to parameter fine-tuning. To address this, we propose Nullify, a training-free, non-destructive activation steering method for LLM unlearning. 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.