Unverified50% confidenceFactExact time
Through targeted teacher intervention, SSD avoids the low-signal state that readily arises in full-policy rollouts, because the teacher provides signals only at positions where knowledge injection is genuinely needed.
1
Sources
50%
Confidence
Long-term
Relevance
11/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe design of SSD keeps training rollouts close to the student's own test-time behavior, avoiding the problems caused by distribution shift in off-policy methods.76% similarUnverifiedSeTPO introduces teacher signals only for low-reward trajectories, uses reverse KL divergence to derive token-level teacher feedback, and incorporates it into the policy advantage function.70% similarUnverifiedThe paper observes that supervision signals from a fixed teacher become increasingly less worthwhile as the student model's capabilities improve66% similarUnverifiedThe core design idea of SeTPO is: the relationship between teacher guidance and student exploration is not necessarily zero-sum, and selective intervention can provide precise help when the student needs it without suppressing its exploration ability.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1155429API
curl https://kongchang.com/api/v1/knowledge/claims/1155429MCP
get_claim(id=1155429)