Emergent misalignment occurs because fine-tuning amplifies target features that overlap geometrically with harmful ones in superposition, and filtering samples near toxic features mitigates it.
I’m mostly interested in your thoughts about humans and AIs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Understanding Emergent Misalignment via Feature Superposition Geometry
Emergent misalignment occurs because fine-tuning amplifies target features that overlap geometrically with harmful ones in superposition, and filtering samples near toxic features mitigates it.