arXiv Artificial Intelligence

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

1 hour ago 09.10.2026 07:00 👁 1 views
Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning

Quick summary

arXiv:2610.10655v1 Announce Type: cross Abstract: 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 st

Key takeaways

  • arXiv:2610.10655v1 Announce Type: cross Abstract: 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.

Why it matters

The significance is not only the legal text but how it changes product design. Decisions around “Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning” may reshape data collection, model training, output accountability and market access.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗