Samuel F. Brown

~Samuel_F._Brown1

3

论文总数

1.5

年均投稿

4.7

平均评分

接收情况1/3

会议分布

ICLR

2

NeurIPS

1

发表论文 (3 篇)

20251 篇

AI Sandbagging: Language Models can Strategically Underperform on Evaluations

ICLR 2025Poster

20242 篇

AI Sandbagging: Language Models can Strategically Underperform on Evaluations

NeurIPS 2024Rejected

Tall Tales at Different Scales: Evaluating Scaling Trends For Deception in Language Models

ICLR 2024Rejected

合作者 (7)

Felix Hofstätter3 篇

Francis Rhys Ward3 篇

Oliver Jaffe3 篇

Teun van der Weij2 篇

Harriet Mary Wood1 篇

Louis Alexander Thomson1 篇

Patrik Bartak1 篇