5 papers
Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
Yicheng Lang, Yihua Zhang, Chongyu Fan +3
Large language model (LLM) unlearning aims to surgically remove the influence of undesired data or knowledge from an existing model while preserving its utility on unrelated tasks.…
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
Chongyu Fan, Jinghan Jia, Yihua Zhang +3
The LLM unlearning technique has recently been introduced to comply with data regulations and address the safety and ethical concerns of LLMs by removing the undesired data-model i…
Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
Changchang Sun, Ren Wang, Yihua Zhang +5
Machine unlearning (MU), which seeks to erase the influence of specific unwanted data from already-trained models, is becoming increasingly vital in model editing, particularly to…
SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?
Haomin Zhuang, Yihua Zhang, Kehan Guo +4
Recent advancements in LLMs unlearning have shown remarkable success in removing unwanted data-model influences while preserving the model's utility for legitimate knowledge. Despi…
Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models
Yize Li, Yihua Zhang, Sijia Liu +1
Despite the remarkable generation capabilities of Diffusion Models (DMs), conducting training and inference remains computationally expensive. Previous works have been devoted to a…