Cite
Notes
Only stored in your browser.
Attribution
Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
arXiv 2025
from 1 papers
Chak Tou Leong
Jaehong Yoon
Jinjin Gu
Linyi Yang
Qingyu Yin
Wenjie Li
Wenxuan Huang
Xiting Wang
YunXing