Unverified50% confidenceFactExact time
交叉熵损失函数鼓励模型将正确类别的logit推向无穷大，导致深度网络预测过于确定
1
Sources
50%
Confidence
Long-term
Relevance
7/9/2026
First Seen
Sources
元认知反馈：用强化学习让大模型准确表达不确定性
hackernewshackernews7/7/2026
Related Claims
UnverifiedThe binary cross-entropy loss formula is -[y·log(p) + (1-y)·log(1-p)], where y is the true label and p is the model's predicted probability for the positive class.69% similarUnverified目前双重下降的严格理论证明主要在线性模型和随机特征模型等简化设定下给出，深度非线性网络的完整数学刻画仍是开放问题67% similarUnverified大模型中的参数在数学上是神经网络每条连接边上的权重数值和偏置值，训练前随机初始化，通过反向传播算法和梯度下降不断调整65% similarUnverifiedThe degree of model memorization is highly correlated with the number of data repetitions; when the number of parameters greatly exceeds the information entropy of the training data, the model tends to memorize rather than generalize.64% similarUnverified自回归大模型推理瓶颈并非计算量而是内存带宽，推测解码通过拒绝采样保证输出分布与原始大模型完全一致63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/319107API
curl https://kongchang.com/api/v1/knowledge/claims/319107MCP
get_claim(id=319107)