Verified65% confidenceFactExact time
Noise information in the context degrades model reasoning accuracy in a nonlinear manner
3
Sources
65%
Confidence
Long-term
Relevance
7/7/2026
First Seen
Sources
Related Claims
UnverifiedHard negative samples (audio similar to the target keyword but that should not trigger, such as homophones and similar phrases) can force the model to focus on truly discriminative features, thereby reducing false activations in real environments, and are more effective than simply increasing the amount of positive samples.77% similarUnverifiedHigh bias means the model is too simple and leads to underfitting, while high variance means the model has learned noise and leads to overfitting, and the two tend to trade off against each other.76% similarUnverifiedThe variance σ²(x) captures a mixture of epistemic uncertainty and aleatoric uncertainty, where the former reflects the model having seen little data and the latter reflects the inherent noise in the data itself.75% similarUnverifiedIf the specified duration exceeds the actual amount of content provided, the model will fill the gap with meaningless noise.74% similarUnverifiedIn financial text prediction, a decrease in training loss does not mean the model has learned a generalizable signal, because the labels themselves are extremely noisy and the model may simply be fitting noise.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/149098API
curl https://kongchang.com/api/v1/knowledge/claims/149098MCP
get_claim(id=149098)