Aaron Jiaxun Li

~Aaron_Jiaxun_Li1

4

论文总数

2.0

年均投稿

5.5

平均评分

接收情况2/4

会议分布

ICLR

3

COLM

1

发表论文 (4 篇)

20251 篇

More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness

20243 篇

Improving Prototypical Part Networks with Reward Reweighing, Reselection, and Retraining

ICLR 2024Rejected

Certifying LLM Safety against Adversarial Prompting

ICLR 2024Rejected

Certifying LLM Safety against Adversarial Prompting

COLM 2024Poster

合作者 (8)

Himabindu Lakkaraju3 篇

Aounon Kumar2 篇

Chirag Agarwal2 篇

Soheil Feizi2 篇

Suraj Srinivas2 篇

Satyapriya Krishna1 篇

Robin Netzorg1 篇