Ningyuan Zhao

large language model (3) machine unlearning (3) sensitive content removal (2) model merging (2) model fine-tuning (1) knowledge forgetting (1) selective forgetting (1) neighborhood consistency (1) knowledge retention (1) knowledge erasure (1) reverse optimization (1) selective erasure (1) belief robustness (1) self consistency (1) contextual interference (1) model compression (1) structure aware training (1) knowledge editing (1) model unlearning (1) knowledge unlearning (1)