arXiv Machine Learning
RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 3
PURGE: Projected Unlearning via Retain-Guided Erasure
arXiv:2606. 03808v1 Announce Type: cross Abstract: We propose PURGE, a machine unlearning algorithm built on a simple but an under-exploited observation: continual learning (CL) and machine unlearning (MU) which are fundamentally dual problems.
arXiv Machine Learning
Oct 7
When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting
arXiv:2610.08718v1 Announce Type: cross Abstract: Knowledge that a language model appears to forget during finetuning often remains stored and can be recovered, a phenomenon called spurious forgettin...
arXiv AI
Jul 3
Locality-Aware Continual Unlearning for Diffusion Models
arXiv:2512. 02657v2 Announce Type: replace-cross Abstract: Real-world deployment of text-to-image diffusion models requires continual concept removal as new privacy, copyright, or safety obligations arise over time.
arXiv Machine Learning
Jun 5
Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance
arXiv:2606. 06320v1 Announce Type: new Abstract: Machine unlearning aims to remove targeted knowledge from a trained model while preserving its general capabilities.
arXiv Computation and Language
Oct 8
A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never Speaks
arXiv:2610.09835v1 Announce Type: new Abstract: Continual pre-training and fine-tuning in Large Language Models (LLMs) inevitably induce catastrophic forgetting, typically mitigated by replay using o...
arXiv Machine Learning
Oct 2
Contrastive Representation Shaping for LLM Unlearning
arXiv:2601.22028v2 Announce Type: replace Abstract: Most LLM unlearning methods aim to approximate retrain-from-scratch behaviors with minimal distribution shift, often via alignment-style objectives...