Philipp Zimmermann
← Back to Newsletter

Paper Library

Collection of AI Security research papers

Showing 97 papers total

May 19 - May 25, 2025

1 paper

Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary

Licheng Pan, Yongqi Tong, Xin Zhang, Xiaolu Zhang, Jun Zhou, Zhixuan Chu
2025-05-23
safety
2505.18325v2