Keyi Kong

~Keyi_Kong1

2

论文总数

2.0

年均投稿

5.8

平均评分

接收情况2/2

会议分布

NeurIPS

1

ICLR

1

发表论文 (2 篇)

20242 篇

Perplexity-aware Correction for Robust Alignment with Noisy Preferences

NeurIPS 2024Poster

An LLM can Fool Itself: A Prompt-Based Adversarial Attack

ICLR 2024Poster

合作者 (6)

Jingfeng Zhang2 篇

Mohan Kankanhalli2 篇

Lizhen Cui1 篇