Unverified50% confidenceFactExact time
Deep learning models are generally prone to overconfidence, where the probability values output by a model do not truly reflect the actual probability of its predictions being correct — a phenomenon known as poor calibration.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe academic community refers to the phenomenon of significant deviation between a model's confidence and its actual accuracy as Poor Calibration.79% similarUnverifiedTop academic deepfake detectors can see their accuracy plummet from 99% to below 60% when faced with previously unseen generative models, a phenomenon known as the cross-model generalization problem.71% similarUnverifiedMultiple independent studies in 2023 showed that some top models scored extremely high on standard mathematical reasoning tests but performed significantly worse on equivalent rephrased versions, indicating that the models learned test patterns rather than genuine reasoning ability.71% similarUnverified研究数据表明，在数学竞赛级别问题上，启用深度推理的模型准确率可从不足30%提升至80%以上68% similarUnverified困惑度是测试集上每个token平均负对数似然的指数，值越低代表模型对语料的预测越准确67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/894772API
curl https://kongchang.com/api/v1/knowledge/claims/894772MCP
get_claim(id=894772)