Unverified50% confidenceFactExact time
In continual learning, standard confidence scores shift systematically as tasks progress: the model is overconfident on inputs from recent tasks and gives muddled confidence for old tasks and truly unknown inputs.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRecency bias refers to the model repeatedly encountering the latest task data at the end of training, causing the decision boundary and output confidence to skew toward recent tasks, rendering threshold-based OOD discrimination ineffective, and this cannot be corrected by simple temperature scaling or post-processing.78% similarVerifiedDrift detection involves a trade-off: setting the threshold too sensitively leads to frequent false alarms and unnecessary retraining, while setting it too loosely may allow model performance to continuously degrade without being detected.76% similarVerifiedOn convergent tasks, there is a clear performance saturation phenomenon after models reach a certain scale, where continued increases in parameter count or training data yield rapidly diminishing marginal contributions to accuracy.76% 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.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073718API
curl https://kongchang.com/api/v1/knowledge/claims/1073718MCP
get_claim(id=1073718)