DuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation
DuoOPD is introduced, in which the student's outcome sets the direction of feedback and the joint teacher-student outcome decides how the teacher supports it: when only the teacher succeeds, its verified answer becomes context for scoring the student's failed response.
Ao Yu, Weibo Gao, Heng Zhou et al.
· 0 citations