Xin Zhang

~Xin_Zhang38

2

论文总数

2.0

年均投稿

6.1

平均评分

接收情况1/2

会议分布

NeurIPS

1

ICLR

1

发表论文 (2 篇)

20252 篇

EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions

NeurIPS 2025Poster

ShieldHead: Decoding-time Safeguard for Large Language Models

ICLR 2025Rejected

合作者 (12)

Xiaofeng Mao2 篇

Chong Teng1 篇

Donghong Ji1 篇

Xiaorui Wu1 篇

Yuxiang Peng1 篇