Unverified50% confidenceFactExact time
Recency 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.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedOn 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.79% similarUnverifiedIn 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.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% similarUnverified端到端模型的核心优势在于避免模块间信息损失和误差累积，但代价是可解释性低、对训练数据分布敏感、难以应对长程推理任务74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073721API
curl https://kongchang.com/api/v1/knowledge/claims/1073721MCP
get_claim(id=1073721)