Understanding the Role of Prompt Template in Knowledge Distillation for Safety Alignment
Prior research has demonstrated that the choice of prompt template during Supervised Fine-Tuning (SFT) significantly impacts the robustness of safety alignment afterwards. However, the influence of template selection during Knowledge Distillation (KD) from teacher to student remains largely unexplored. Thus, we fill th...
Anjila Budathoki, Manish Dhakal, Benjamin M. Ampel et al.
· 0 citations