Unverified50% confidenceFactExact time
D²-OPD optimizes the student model using forward KL divergence, so as to also cover low-probability tokens in the teacher distribution.
1
Sources
50%
Confidence
Long-term
Relevance
11/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGAD-RL weights the forward KL divergence using the student's predicted probability for the teacher's Top-1 token, suppressing local auxiliary updates when the student's support for the teacher's recommended token is low76% similarUnverifiedThe core operation of SimOPD is to make the similarity distribution induced by the response representations output by the student model approach the similarity distribution induced by the teacher model's internal representations, using KL divergence or cross-entropy loss to bring the two distributions closer.75% similarUnverifiedExperiments show that LoopOPD significantly improves the model's mathematical reasoning ability, and D-LoopOPD brings further gains through dynamic teacher updates.71% similarUnverifiedDNO-Prct uses an iterative process: in each round, online sampling is performed on the policy model, an LLM scores the samples together with the teacher model's golden answers, large-margin preference pairs are selected, and finally a DPO-style contrastive update is performed.71% similarUnverifiedForward KL tends to make the student policy cover all modes of the teacher policy, learning comprehensively but possibly not precisely enough; reverse KL tends to make the student policy concentrate on the high-probability regions of the teacher policy, learning precisely but possibly missing certain modes.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1141998API
curl https://kongchang.com/api/v1/knowledge/claims/1141998MCP
get_claim(id=1141998)