Naomi Bashkansky

~Naomi_Bashkansky1

3

论文总数

1.5

年均投稿

6.6

平均评分

接收情况2/3

会议分布

COLM

1

ICLR

1

NeurIPS

1

发表论文 (3 篇)

20251 篇

Incidental Polysemanticity: A New Obstacle for Mechanistic Interpretability

ICLR 2025Rejected

20242 篇

Measuring and Controlling Instruction (In)Stability in Language Model Dialogs

COLM 2024Poster

Many-shot Jailbreaking

NeurIPS 2024Poster

合作者 (20)

Rylan Schaeffer2 篇

Fernanda Viégas1 篇

Hanspeter Pfister1 篇

Kenneth Li1 篇

Martin Wattenberg1 篇

Tianle Liu1 篇

Alex Tamkin1 篇