Unverified50% confidenceFactExact time
On-policy distillation applies teacher supervision on trajectories generated by the student itself, enabling better handling of the exposure bias problem.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
Cite This Claim
Stable URI
https://kongchang.com/claim/1001175API
curl https://kongchang.com/api/v1/knowledge/claims/1001175MCP
get_claim(id=1001175)