2 citations · 2 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
HumorReject: Decoupling LLM Safety from Refusal Prefix via A Little Humor
Zihui Wu, Haichang Gao, Jiacheng Luo +1
Large Language Models (LLMs) commonly rely on explicit refusal prefixes for safety, making them vulnerable to prefix injection attacks. We introduce HumorReject, a novel data-drive…
cs.LG2023
AdvFunMatch: When Consistent Teaching Meets Adversarial Robustness
Zihui Wu, Haichang Gao, Bingqian Zhou +1
\emph{Consistent teaching} is an effective paradigm for implementing knowledge distillation (KD), where both student and teacher models receive identical inputs, and KD is treated…