AI Paper Atlas

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

Towards Unbounded Machine Unlearning

Meghdad Kurmanji, Peter Triantafillou, Jamie Hayes, Eleni Triantafillou

NeurIPS 2023 · Continual learning › Continual fine-tuning of LLMs · approach: Machine unlearning by selective forgetting · 28 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 rewinding to SCRUB for selective unlearning (ablation)SCRUB · CIFAR-10 selective, ResNetBasic MIA accuracy (%): 78.00 -> 58.67Improved
add rewinding to SCRUB for class unlearning (ablation)SCRUB · CIFAR-10 class, ResNetBasic MIA accuracy (%): 52.20 -> 52.20No clear effect
use SCRUB instead of Bad-T for resolving confusionunlearning method · CIFAR-5 RC ResNetFgt test error (%): 27.0 -> 19.7Improved
use SCRUB instead of fine-tuning on retain setunlearning method · CIFAR-5 RC ResNetFgt test error (%): 79.3 -> 19.7Improved
use contrastive teacher-student objective with alternating max/min steps instead of plain NegGrad+unlearning · CIFAR-5 RC ResNetFgt test error (%): 69.0 -> 19.7Improved
use Bad-T (move toward bad teacher) instead of SCRUBunlearning · RC ResNetIC test error (%): 19.0 -> 47.3Hurt
vary SCRUB hyperparameters alpha and gamma over [0.1,3] (ablation)SCRUB · CIFAR-10retain errorNo clear effect

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