AI Paper Atlas

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

Forget by Uncertainty: Orthogonal Entropy Unlearning for Quantized Neural Networks

Tian Zhang, Yujia Tong, Junhao Dong, Ke Xu, Yuze Wang, Jingling Yuan

ICML 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Machine unlearning by selective forgetting · 0 citations (OpenAlex)

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
add gradient orthogonal projection (ablation)OEU · CIFAR-100 random forgetting 30% (ResNet-18 4-bit)Average Gap: 3.53 -> 1.98Improved
add entropy-guided unlearning (vs wrong-label learning) (ablation)OEU · CIFAR-100 random forgetting 30% (ResNet-18 4-bit)Average Gap: 3.98 -> 1.98Improved
use layer-wise instead of global projection (ablation)OEU · CIFAR-100 random forgetting 30% (ResNet-18 4-bit)Average Gap: 5.40 -> 1.98Improved
OEU vs Q-MULOEU vs Q-MUL · CIFAR-10 random forgetting 10% (ResNet-18 4-bit)Average Gap: 1.30 -> 0.58Improved
OEU vs Q-MULOEU vs Q-MUL · CIFAR-100 random forgetting 10% (ResNet-18 4-bit)Average Gap: 3.11 -> 3.08No clear effect
OEU vs Q-MULOEU vs Q-MUL · CIFAR-100 random forgetting 50% (ResNet-18 4-bit)Average Gap: 7.06 -> 3.67Improved
apply OEU to full-precision ResNet-18OEU · CIFAR-100 random forgetting 10%Average Gap: 3.60Improved
apply OEU with PACT and DSQ quantizers instead of LSQ+OEU · CIFAR-100 random forgetting 10%Average Gap: -60.5% (PACT), -56.2% (DSQ) vs Q-MULImproved
use gradient ascent/fine-tuning (baselines) vs retrainFT/GA · CIFAR-100 random forgetting 10% (ResNet-18 4-bit)Average Gap: 17.43 (FT), 17.69 (GA)Hurt

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