Tinghao Xie

~Tinghao_Xie1

5

论文总数

2.5

年均投稿

6.3

平均评分

接收情况5/5

会议分布

ICLR

5

发表论文 (5 篇)

20253 篇

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

ICLR 2025Poster

Fantastic Copyrighted Beasts and How (Not) to Generate Them

ICLR 2025Poster

On Evaluating the Durability of Safeguards for Open-Weight LLMs

ICLR 2025Poster

20242 篇

BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection

ICLR 2024Poster

Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

合作者 (20)

Peter Henderson4 篇

Prateek Mittal4 篇

Xiangyu Qi4 篇

Yangsibo Huang3 篇

Danqi Chen2 篇