ZeroUnlearn is a few-shot unlearning method that maps sensitive inputs to neutral states and enforces representational orthogonality through a closed-form multiplicative update, outperforming baselines while preserving utility.
over-correction
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
-
ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
ZeroUnlearn is a few-shot unlearning method that maps sensitive inputs to neutral states and enforces representational orthogonality through a closed-form multiplicative update, outperforming baselines while preserving utility.