#Preventative Steering

1 stories · 0 in 7 days · 0 in 30 days

Stories, products and papers tagged "Preventative Steering", newest first.

Sep 10

Preventative Steering in Adversarial Fine-Tuning

PIS improves safety robustness in Qwen2.5 and Gemma-3 models while reducing harmful trait expression, offering a practical solution for model developers.

#Preventative Steering #Qwen2.5 #Gemma-3 #cyber defense

arXiv cs.AI@Jing Guan et al. (6)Source