Uncovering Safety Risks in Open-source LLMs through Concept Activation Vector.

Zhihao Xu Ruixuan Huang Xiting Wang Fangzhao Wu Jing Yao Xing Xie

Published in: CoRR (2024)

Keyphrases

open source
open source software
source code
decision making
real time
united states
feature vectors
risk factors
risk analysis