Unverified50% confidenceFactExact time
Large models rely on a pseudorandom number generator as the sampling source when generating text, and if that pseudorandom source can be predicted, the generation process no longer possesses true unpredictability.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOutput examples are key to suppressing randomness and hallucinations in large models: without examples responses may be irregular, but once a formatted reference is provided the output will closely follow the expected template.77% similarUnverified大语言模型本质上是概率系统，其输出具有随机性，内部推理过程是不透明的黑盒76% similarUnverifiedLLM的输出本质上是随机过程的采样结果，即使相同输入不同随机种子也会导致不同输出，无法像传统软件那样100%可预测76% similarUnverifiedCode cells yield the same result every time they are executed under a fixed random seed, whereas a pure 'prompt → result' approach introduces the non-determinism of large models.75% similarUnverified大语言模型是概率性、随机性的，它根据之前出现的词元来预测下一个词元75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1026916API
curl https://kongchang.com/api/v1/knowledge/claims/1026916MCP
get_claim(id=1026916)