Unverified50% confidenceFactExact time
生成式模型建模联合概率 P(x,y) 或数据分布 P(x)，而判别式模型直接建模条件概率 P(y|x)；生成模型在小样本时更具优势，判别模型在大数据量时通常表现更好
1
Sources
50%
Confidence
Long-term
Relevance
8/29/2026
First Seen
Sources
Related Entities
Related Claims
Unverified生成式模型建模联合概率 P(x,y) 或数据分布 P(x)，判别式模型直接建模条件概率 P(y|x)，该区分最初由 Andrew Ng 和 Michael Jordan 在 2001 年的论文中系统比较80% similarUnverifiedA prompt is essentially the 'condition' for the model; the more precise the condition, the more concentrated the model's probability distribution becomes on the user's desired output, rather than being spread across all directions.78% similarUnverified生成模型在小样本时更具优势，判别模型在大数据量时通常表现更好72% similarUnverifiedThe posterior distribution is obtained via Bayes' theorem: p(θ|x) ∝ p(x|θ)·p(θ), combining prior knowledge with the data likelihood.72% similarUnverifiedMTP adds multiple prediction heads to the model's output layer, enabling the model to simultaneously predict the probability distribution of the next N tokens in a single forward pass, achieving 2–4x inference acceleration without sacrificing generation quality.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/817173API
curl https://kongchang.com/api/v1/knowledge/claims/817173MCP
get_claim(id=817173)