Unverified50% confidenceFactExact time
Autoregressive generation outputs are affected by sampling strategies (hyperparameters such as temperature and top-p), making it difficult to guarantee completely consistent outputs
1
Sources
50%
Confidence
Long-term
Relevance
9/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTop-p（核采样）通过限定候选token的累积概率范围来控制输出多样性，与Temperature配合使用可实现更精细的输出调节74% similarUnverifiedTemperature=0（贪心采样）也不能保证模型输出的确定性，至少有三个原因：浮点运算非结合性、MoE路由不确定性、服务端配置漂移73% similarVerifiedThe non-determinism of LLMs stems from sampling strategies; the Temperature parameter controls the randomness of the output distribution, while Top-p and Top-k further constrain the range of candidate tokens.73% similarUnverifiedtop-p（核采样）等参数同样影响大模型输出的不确定性72% similarUnverifiedTemperature controls the flatness of the sampling distribution; a higher value tends toward selecting lower-probability words, while Top-p dynamically narrows the candidate vocabulary set through a cumulative probability threshold.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/954240API
curl https://kongchang.com/api/v1/knowledge/claims/954240MCP
get_claim(id=954240)