AI Paper Atlas

Research map / Continual learning / Continual fine-tuning of LLMs

Unlearning Isn’t Forgetting: Revealing Hidden Leakage in Class Unlearning Evaluations

Ali Ebrahimpour-Boroojeny, Yian Wang, Hari Sundaram

ICML 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Machine unlearning by selective forgetting

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
match retrained model behavior with tilted reweighting instead of existing unlearning objectivesclass unlearning of CIFAR-10 ResNet18 · CIFAR-10 class unlearningCMIA accuracy: SCAR 71.93 -> TREW 95.82 (Retrain 95.27)Improved
use TREW on class unlearningfine-tuning unlearning · CIFAR-10 U-LiRA (ResNet18)U-LiRA accuracy (%): FT 72.57 -> TREW 71.12; TREW-2R 67.72Improved
keep standard MIA score high while ignoring class geometry (existing methods)existing unlearning methods such as SalUn and SCRUB · CIFAR-10 class unlearningCMIA accuracy: SalUn MIA 96.33, CMIA 9.62 vs Retrain 95.27Hurt
use TREW instead of fine-tuning with plain forget label reassignmentFT baseline · CIFAR-10 class unlearningaverage gap to Retrain: -5.80 -> -0.59Improved
restrict TREW updates to two random layers (TREW-2R) (ablation)TREW · CIFAR-10 class unlearning (ResNet18)average gap to Retrain: -0.59 -> -1.09No clear effect
use class-level similarity scores instead of sample-dependent similarity (ablation)TREW · class unlearningmatch to RetrainImproved
use positive tilt beta rather than none, avoiding extreme values (ablation)TREW · class unlearningcloseness to RetrainImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy