ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models

Jiahui Guang, Haiyan Wang, Yingjie Zhu, Cuiyun Gao, Jing Li, Di Shao, Zhaoquan Gu

Thursday at 04:00

5 Views

0 Comments

arXiv:2605.15687v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) may memorize sensitive cross-modal information during pretraining, making machine unlearning (MU) crucial. Existing methods typically evaluate unlearning effectiveness based on output deviations, while overlooking the generation quality after...

Read the full article at the source.

Read Original Article

Was this helpful?