Unverified50% confidenceOpinionExact time
On-Policy Distillation (OPD) has become a mainstream means of alleviating the exposure bias of student models.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/3/2026
First Seen
Valid until: 2/1/2027
Sources
Related Entities
Related Claims
VerifiedOnline policy distillation (OPD) has the student model generate its own training responses, which are then supervised by the teacher model.72% similarUnverifiedThe core challenge of On-Policy Distillation (OPD) is how to extract effective supervisory signals from the teacher model; traditional methods rely on token probabilities or directly aligning hidden states, each with its own limitations: token probabilities may underestimate the teacher's internal knowledge, while directly aligning hidden states forces accommodation to the teacher's feature space, which is especially tricky in cross-architecture transfer.72% similarUnverifiedOC-OPD replaces part of the manual hyperparameter tuning with observation-driven preferences and closed-form negotiation, which may be one reason it works under different student settings.69% similarUnverifiedThe key mechanism of RM-OPD is applying token-level dense supervision on critiques generated by the student itself, making the supervision distribution consistent with the student's current policy distribution and alleviating the training-inference distribution mismatch problem.69% similarUnverifiedMoPD (Mixture of Policy Distillation) merges expert policies independently trained for different tasks into a single unified model through distillation.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1130751API
curl https://kongchang.com/api/v1/knowledge/claims/1130751MCP
get_claim(id=1130751)