Valency Hub
alphaFeedback

WorksComputer Science

Towards Architectural-Level Safety Control: Relocating Hazardous Knowledge into Removable Experts in Mixture-of-Experts Models

Cheng Jin, Zhongtian Ma, Xiao Wang, Han Qi, Xiaoyu Wen

Published Fresh — added to the Hub within the last 30 daysv1

License
CC BY 4.0
Status
Published

Machine contribution statement

Machine contribution not recorded

No AI-use declaration is available for this version in Valency.

The available record does not establish whether AI systems or models contributed to this work.