MASC achieves competitive forget-retain trade-offs in language model unlearning at lower computational cost via margin self-correction and an online stopping criterion on TOFU, MUSE News, and MUSE Books.
2406.01983 , archivePrefix=
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
SHRED performs retain-set-free unlearning by selecting lowest-probability tokens as forget positions and applying a single KL self-distillation objective that demotes logits only at those positions.
citing papers explorer
-
Fast Unlearning at Scale via Margin Self-Correction
MASC achieves competitive forget-retain trade-offs in language model unlearning at lower computational cost via margin self-correction and an online stopping criterion on TOFU, MUSE News, and MUSE Books.
-
SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
SHRED performs retain-set-free unlearning by selecting lowest-probability tokens as forget positions and applying a single KL self-distillation objective that demotes logits only at those positions.