Evaluating Proactive Risk Awareness of Large Language Models
arXiv:2602.20976v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly embedded in everyday decision-making, their safety responsibilities extend beyond reacting to explicit harmful …
Xuan Luo, Yubin Chen, Zhiyu Hou, Linpu Yu, Geng Tu, Jing Li, Ruifeng Xu
5 views
