arxiv
PublishedMay 11, 2026 at 4:00 AM
—neutral
Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
Publisher summary· verbatim
arXiv:2605.05995v2 Announce Type: replace-cross Abstract: The safety alignment of Large Language Models (LLMs) remains vulnerable to Harmful Fine-tuning (HFT). While existing defenses impose constraints on parameters, gradients, or internal representations, we observe that they can be effectively ci
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
The Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗