Nina Rimsky

~Nina_Rimsky1

2

论文总数

2.0

年均投稿

6.5

平均评分

接收情况2/2

会议分布

NeurIPS

2

发表论文 (2 篇)

20242 篇

Many-shot Jailbreaking

NeurIPS 2024Poster

Refusal in Language Models Is Mediated by a Single Direction

NeurIPS 2024Poster

合作者 (20)

Alex Tamkin1 篇

Ansh Radhakrishnan1 篇

Carson Denison1 篇

Daniel J Ford1 篇

David Duvenaud1 篇

Deep Ganguli1 篇

Esin DURMUS1 篇