Unverified50% confidenceFactExact time
Opportunity-normalized accuracy is computed as (model accuracy − random-guess accuracy) / (1 − random-guess accuracy).
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
Unverified泰特洛克的研究得出结论：专家预测的准确率仅略高于随机猜测，甚至不如简单的统计基准线76% similarUnverifiedResearchers have proposed having models explicitly output probabilities, or estimating reliability by sampling multiple times and measuring answer consistency (self-consistency).76% similarUnverifiedIn class-imbalance scenarios, a model can achieve seemingly impressive accuracy by always predicting the majority class, a phenomenon known as the Accuracy Paradox.75% similarUnverifiedMacro-average accuracy first computes the accuracy of each class separately and then takes the arithmetic mean, making it more sensitive to the performance of minority classes; overall accuracy is the proportion of all samples predicted correctly and is easily affected by the class sample size distribution.75% similarUnverifiedConfidence is typically represented by the product of per-token probabilities or the sum of their logarithms.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1105835API
curl https://kongchang.com/api/v1/knowledge/claims/1105835MCP
get_claim(id=1105835)