most citedMEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts

2 citations · 3 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2025

Probing the Robustness of Large Language Models Safety to Latent Perturbations

Tianle Gu, Kexin Huang, Zongqi Wang +7

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts c…