Unverified50% confidenceFactExact time
D²-OPD determines the extrapolation direction by adaptively weighted combination of the teacher model's post-training offset and the initial student-teacher gap.
1
Sources
50%
Confidence
Long-term
Relevance
11/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedD²-OPD's per-prefix hard KL constraint has controllable computational overhead, and the adaptive direction combination requires no additional teacher forward passes, giving it good feasibility in practical training.78% similarVerifiedOnline policy distillation (OPD) has the student model generate its own training responses, which are then supervised by the teacher model.74% similarUnverifiedCoRD's design automatically anneals the replacement strength over training: as the student gradually learns the teacher-preferred tokens, the two distributions converge and the replacements naturally decrease.73% similarUnverifiedOffline distillation trains the student using a static dataset pre-generated by the teacher model, which leads to the problem of covariate shift.72% similarUnverifiedThe paper categorizes existing OPSD approaches into two types: one where the teacher is fixed throughout training and has access to the full reference; the other where the teacher is unchanged within each response but adaptively varies across responses in the degree of exposure to partial reference.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1141997API
curl https://kongchang.com/api/v1/knowledge/claims/1141997MCP
get_claim(id=1141997)