Unverified50% confidenceFactExact time
The models' self-reported uncertainty had a weak ability to rank prediction errors, with a Spearman rank correlation coefficient of at most 0.46.
1
Sources
50%
Confidence
Long-term
Relevance
11/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Spearman correlation coefficient between tool description scores and correct model selection was only 0.04, with almost no statistical association.78% similarUnverified困惑度是测试集上每个token平均负对数似然的指数，值越低代表模型对语料的预测越准确76% similarUnverifiedThe oracle router knows in advance which cases the small model will get wrong, sends only the wrong requests to the large model, and achieves accuracy comparable to always using the large model at only 29% of the cost.75% similarUnverified仅用小模型策略的每正确答案成本最低($0.0004)但准确率仅33%，说明没有准确率底线的每正确答案成本指标具有误导性75% similarUnverifiedRanked by question difficulty, persistence rate was 91.4% on the 60 questions that all models answered correctly, but only 73.5% on the 52 questions that at least one model got wrong, indicating that sycophancy tracks uncertainty.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1124958API
curl https://kongchang.com/api/v1/knowledge/claims/1124958MCP
get_claim(id=1124958)