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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pan, Licheng, Tong, Yongqi, Zhang, Xin, Zhang, Xiaolu, Zhou, Jun, Chu, Zhixuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!