Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning
arXiv:2610.10655v1 Announce Type: new 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 ut…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-09 04:00 · arXiv cs.LG
Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning