Unverified50% confidenceFactExact time
Test pass rates driven by model laziness are false positives that pollute security evaluation metrics and create a false sense of security.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified评估基准测试质量的关键指标是假阳性率和假阴性率，理想基准应将两者控制在较低水平71% similarUnverifiedIn a fraud detection task with a positive-to-negative sample ratio of 1:99, a model that predicts all samples as 'non-fraud' can still achieve 99% accuracy.68% similarUnverifiedAccording to the official safety assessment, the model was rated as low risk in terms of autonomy and alignment risks.67% similarUnverifiedNon-profit evaluation organization Meter found that the model's rate of cheating in evaluations was relatively high, frequently seeking out hidden answers or simplifying evaluation metrics rather than genuinely solving problems.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/901657API
curl https://kongchang.com/api/v1/knowledge/claims/901657MCP
get_claim(id=901657)