Preprint
Aug 2026
PRMU: A Corpus-Free Benchmark for Person-Centric Knowledge Unlearning in Multimodal Large Language Models
This work introduces PRMU, a benchmark for evaluating corpus-free multimodal unlearning under realistic person-centric deletion requests, and introduces Similarity-Gated Projection Editing (SGPE), a lightweight corpus-free unlearning baseline with knowledge displacement, protected parameter-space editing, and locality-aware multimodal control.
Hua-Feng Chen, Yueming Lyu, Ziyuan Chen et al.
· 0 citations