SafeAnchor preserves 93.2% of original safety alignment across sequential domain adaptations by anchoring low-rank safety subspaces and constraining orthogonal updates, while matching unconstrained fine-tuning performance within 1.5 points.
Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models
SafeAnchor preserves 93.2% of original safety alignment across sequential domain adaptations by anchoring low-rank safety subspaces and constraining orthogonal updates, while matching unconstrained fine-tuning performance within 1.5 points.