Unverified50% confidenceFactExact time
In knowledge distillation and Ambient SFT, the loss function usually consists of a task loss and a KL divergence regularization term: the former pulls the model output closer to the hard labels, while the latter constrains the model distribution not to deviate too far from the teacher distribution.
1
Sources
50%
Confidence
Long-term
Relevance
11/18/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe core loss functions of contrastive learning (such as InfoNCE and NT-Xent) essentially pull the representations of similar samples closer together while pushing the representations of dissimilar samples further apart.74% similarUnverifiedSFT's loss function treats every token in the trajectory equally and cannot distinguish key decision points from ordinary operations, making it difficult to correct over-exploration.73% similarUnverifiedThe paper proposes JurisCoT-SFT, which computes losses separately for the reasoning chain and the final answer and normalizes them by sequence length so that the learning signals of the two parts are on a comparable scale.73% similarUnverified监督学习本质上是函数逼近问题,通过最小化损失函数实现,常见损失函数包括回归任务的均方误差(MSE)和分类任务的交叉熵(Cross Entropy)72% similarUnverifiedTraining the student model with pixel-level loss functions (L1+MSE) caused the output images to appear gray and flat, resembling an average of all possible results—a classic failure mode of regression-based losses on generative tasks.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1182995API
curl https://kongchang.com/api/v1/knowledge/claims/1182995MCP
get_claim(id=1182995)