ROSU derives a closed-form retain-neutral perturbation for min-max unlearning that bounds retain damage via curvature and improves performance when gradients are aligned.
TOFU: A task of fictitious unlearning for LLMs
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
MANSU achieves the first unlearning method that jointly delivers behavioral forgetting, retain preservation, zero PTQ gap, and structural erasure by circuit-restricted null-space projection plus a per-parameter magnitude floor.
citing papers explorer
-
Retain-Neutral Surrogates for Min-Max Unlearning
ROSU derives a closed-form retain-neutral perturbation for min-max unlearning that bounds retain damage via curvature and improves performance when gradients are aligned.
-
Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
MANSU achieves the first unlearning method that jointly delivers behavioral forgetting, retain preservation, zero PTQ gap, and structural erasure by circuit-restricted null-space projection plus a per-parameter magnitude floor.