Unverified50% confidenceSolutionExact time
The core design of item-space OPD is: rank the document scores output by the student model into a ranked sequence, then feed this list as input to the generative teacher model, which provides conditional feedback based on the list to directly supervise the student model's scores.
1
Sources
50%
Confidence
Long-term
Relevance
11/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIDM uses a fixed item-to-code mapping to combine the student model's probabilities at each code position into a joint item probability, thereby reconstructing a catalog-level item distribution and aligning it with the teacher model's item distribution.68% similarUnverifiedOn-policy distillation (OPD) has the student model generate its own trajectories, and then the teacher model provides supervision signals on those trajectories.67% similarUnverifiedThe ABACUS team instantiated the framework with Kev: the teacher model plans reasoning steps and generates program code, and the frozen judgment model acts as a semantic executor that scores candidate answers for each step.63% similarUnverifiedThe behavior of the ASTEROID student model is guided by expert labels toward a mode approximating Bayesian posterior sampling: when information is insufficient, it selects actions that can distinguish different hidden states, and when information is sufficient, it directly exploits.62% similarUnverifiedIn the learning machine scenario, the ERNIE large model is used to parse problems, generate step-by-step explanations, and adjust answers based on the child's follow-up questions.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125720API
curl https://kongchang.com/api/v1/knowledge/claims/1125720MCP
get_claim(id=1125720)