Verified75% confidenceFactExact time
Mainstream generative large models are based on the Transformer architecture and have a probabilistic selection mechanism during output, which means the same question may produce different answers.
5
Sources
75%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedModern large models are based on the Transformer architecture, and generating each token requires one full forward pass over all the model's parameters.79% similarUnverifiedThe theoretical foundation of prompt engineering lies in the autoregressive generation characteristics of the Transformer architecture, where model output quality is highly dependent on the degree of structure in the input.78% similarUnverifiedIn the Transformer architecture, the computational cost per generated token is approximately proportional to the number of activated parameters; for dense models the activated parameter count equals the total parameter count, while for MoE models the activated parameter count is far smaller than the total parameter count.78% similarUnverifiedIn the Transformer architecture, there is an approximately linear relationship between model parameter count and inference latency.78% similarUnverified在Transformer模型中，追求好的推理（预测行为）与实现完美检索会争夺参数空间，二者相互冲突78% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/905796API
curl https://kongchang.com/api/v1/knowledge/claims/905796MCP
get_claim(id=905796)