TISD: On-Policy Self-Distillation with Trajectory Intervention
A simple branch-regenerate-distill algorithm, Trajectory-Intervention Self-Distillation (TISD), which forces a teacher-selected branch action, returns suffix generation to the student, and distills the full trajectory under the privileged-context-conditioned teacher, support teacher-guided branching as a way to expose...
Taeckyung Lee, Rinat Amankos, Jeonghye Kim et al.
· 0 citations