SHRED achieves retain-set-free LLM unlearning by selecting high-Shannon-information tokens for logit demotion in a single self-distillation KL objective, yielding a superior forget-utility Pareto front on four benchmarks.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
dataset 1polarities
use dataset 1representative citing papers
PrivUn shows privacy unlearning in LLMs produces gradient-driven ripple effects and only shallow forgetting across layers, with new strategies proposed for deeper removal.
Unlearned language models retain low calibration error but show increased shortcut reliance on the TOFU benchmark, extending the reliability paradox to machine unlearning.
citing papers explorer
-
SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
SHRED achieves retain-set-free LLM unlearning by selecting high-Shannon-information tokens for logit demotion in a single self-distillation KL objective, yielding a superior forget-utility Pareto front on four benchmarks.
-
PrivUn: Unveiling Latent Ripple Effects and Shallow Forgetting in Privacy Unlearning
PrivUn shows privacy unlearning in LLMs produces gradient-driven ripple effects and only shallow forgetting across layers, with new strategies proposed for deeper removal.
-
Calibration vs Decision Making: Revisiting the Reliability Paradox in Unlearned Language Models
Unlearned language models retain low calibration error but show increased shortcut reliance on the TOFU benchmark, extending the reliability paradox to machine unlearning.