Narutatsu Ri

~Narutatsu_Ri1

2

论文总数

1.0

年均投稿

5.3

平均评分

接收情况1/2

会议分布

ICML

1

ICLR

1

发表论文 (2 篇)

20251 篇

Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions

ICML 2025Poster

20241 篇

Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations

ICLR 2024Rejected

合作者 (10)

Marzyeh Ghassemi1 篇

Yik Siu Chan1 篇

Yuxin Xiao1 篇

Jacob Steinhardt1 篇

Kathleen McKeown1 篇

Ruiqi Zhong1 篇