Unverified50% confidenceFactExact time
Temperature calibration assumes the validation set and deployment distribution come from the same source; once temporal drift occurs, the calibrated T becomes invalid.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe 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.71% 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70% similarUnverifiedThe LLM-judge approach may give inconsistent conclusions for the same suspicious text when the temperature parameter is non-zero, and attackers can wait for passage by repeatedly retrying.68% similarUnverifiedLLM judge results are affected by factors such as temperature, prompt wording, and model version updates, causing the same set of test cases to potentially produce different conclusions when run at different times.68% similarVerifiedEven when temperature is set to 0, some models still exhibit slight output fluctuations due to floating-point errors in parallel computation.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084096API
curl https://kongchang.com/api/v1/knowledge/claims/1084096MCP
get_claim(id=1084096)