Unverified50% confidenceFactExact time
Under label imbalance, accuracy is highly misleading: a model that always predicts the majority class can score very high on accuracy while missing every positive example.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
Unverified如果参数量充足的模型连几十个样本都无法记住，几乎可以断定存在硬性错误，如标签错位、损失函数计算错误、梯度未正确回传等78% similarUnverifiedTraditional confidence calibration methods mostly rely on model-generated output text or sequence-based probability statistics, making it difficult to capture complex failure patterns in multi-turn agent interactions.77% similarUnverifiedIn multi-class tasks, accuracy becomes distorted when class samples are imbalanced; precision reflects the degree of false positives, recall reflects the degree of false negatives, and the F1 score is the harmonic mean of precision and recall.77% similarUnverifiedIn class-imbalanced scenarios, accuracy alone can be misleading and needs to be combined with a confusion matrix for more fine-grained evaluation.76% similarUnverifiedFine-tuning is worth evaluating in scenarios where the model has adequate information but repeatedly fails to complete tasks as required, with signals including inconsistent output schemas, unstable classification results, and misunderstood domain terminology.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1054180API
curl https://kongchang.com/api/v1/knowledge/claims/1054180MCP
get_claim(id=1054180)