Episode
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation
- Podcast
- Daily Paper Cast
- Published
- Sep 9, 2026
- Duration seconds
- 1281
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/7cb4c5a7
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/eliciting-weak-to-strong-generalization-with-on-policy-reverse-distillation/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/eliciting-weak-to-strong-generalization-with-on-policy-reverse-distillation.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 57 | cs.LG, cs.CL Authors: Youngrok Park, Sangmin Bae, Hojung Jung, Jongwoo Ko, Yunseon Choi, Young Jin Kim, Pashmina Cameron, Aaron Courville, Se-Young Yun Title: Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation Arxiv: http://arxiv.org/abs/2609.08798v1 Abstract: Weak-to-strong generalization asks whether stronger models can learn from weaker supervisors and surpass them. This question is particularly important for successive model generations and multi-domain consolidation, where repeating frontier-scale post-training from scratch can be prohibitively expensive. Yet conventional distillation treats the weak teacher as an optimization target, potentially imposing its capacity ceiling on the student. We introduce On-Policy Reverse Distillation (OPRD), which evaluates the teacher's policy shift relative to its reference policy on student rollouts and amplifies the component of the student's verifier-driven policy gradient along that direction. By rescaling only verifier-supported updates, OPRD preserves the stationary points of policy optimization while accelerating learning beyond the teacher. In both successive model transfer and multi-teacher distillation, OPRD achieves higher performance with fewer student updates than existing RL and distillation approaches. Response-style analysis shows that OPRD students remain closer to models trained with verifier-based RL alone than to their weak teachers, suggesting that teacher guidance accelerates rather than redirects the student's own optimization. Results in conventional strong-to-weak distillation further demonstrate that OPRD effectively combines verifier-driven policy optimization with teacher guidance regardless of capacity ordering.