Unverified70% confidenceFactExact time
Uncalibrated neural networks typically exhibit overconfidence, which is especially pronounced on out-of-distribution data.
2
Sources
70%
Confidence
Long-term
Relevance
9/27/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedNeural networks have an overconfidence defect: even when inputs fall outside the training distribution, the Softmax layer may still output inflated confidence scores.80% similarUnverifiedThe overconfidence of a model answering directly while skipping retrieval is technically referred to as miscalibration, meaning there is a systematic deviation between confidence and actual accuracy.77% similarUnverifiedResearch has found that large language models tend to be overconfident when not specifically optimized, meaning they output high confidence scores but have a relatively high actual error rate.74% similarUnverified深度神经网络天然倾向于过拟合训练分布，对分布外样本的处理能力往往大幅下降72% similarUnverifiedWhen a model faces out-of-distribution questions, its internal probability distribution is often too flat or too sharp, causing confidence to be systematically too high.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/953523API
curl https://kongchang.com/api/v1/knowledge/claims/953523MCP
get_claim(id=953523)