[KongchangAI]
Unverified50% confidenceFactExact time

The complete training objective is L = α·L_CE(y, p_s) + (1-α)·T²·L_KL(p_t^T, p_s^T), where T² is a gradient correction factor introduced by temperature scaling.

1
Sources
50%
Confidence
Long-term
Relevance
9/21/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/937979
API
curl https://kongchang.com/api/v1/knowledge/claims/937979
MCP
get_claim(id=937979)