Unverified50% confidenceFactExact time
The randomness of LLM inference comes from at least three independent sources: the sampling strategy (temperature, top-p), the accumulated error of floating-point operations, and changes in the reduction order of matrix multiplications caused by changes in batch size.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedWhen generating each token, LLMs randomly sample from a probability distribution according to a temperature parameter rather than selecting the deterministic output with the highest probability, thereby producing emergent properties.79% similarUnverified大语言模型（LLM）由于temperature、top-p、top-k等采样策略带有随机性，同一提示词在两次调用中可能产生截然不同的响应79% similarUnverified在LLM引用行为测试中固定随机性需要同时设置temperature和top-p参数并在支持时固定随机种子78% similarVerifiedLLM的不一致性与模型的温度参数和随机采样过程密切相关，同一问题多次调用同一模型可能产生不同答案78% similarUnverifiedEvery step of LLM reasoning involves sampling from a probability distribution, and errors compound in a snowball effect when multiple steps are chained together, whereas code execution either runs correctly or throws an error, with no such thing as approximately correct75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042199API
curl https://kongchang.com/api/v1/knowledge/claims/1042199MCP
get_claim(id=1042199)