Boyi Wei

~Boyi_Wei2

2

论文总数

2.0

年均投稿

6.6

平均评分

接收情况2/2

会议分布

ICLR

2

发表论文 (2 篇)

20252 篇

On Evaluating the Durability of Safeguards for Open-Weight LLMs

ICLR 2025Poster

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

ICLR 2025Poster

合作者 (18)

Peter Henderson2 篇

Prateek Mittal2 篇

Tinghao Xie2 篇

Xiangyu Qi2 篇

Yangsibo Huang2 篇

Matthew Jagielski1 篇

Milad Nasr1 篇