Unverified50% confidenceFactExact time
DocXEval's meta-evaluation found moderate to strong agreement among several faithfulness metrics and complexity metrics, while also identifying some metrics that produce unreliable results.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/28/2026
First Seen
Valid until: 1/26/2027
Sources
Related Entities
Related Claims
UnverifiedFor high-risk scenarios, judging model reliability from CoT text alone is insufficient; it must also be combined with consistency across multiple samples, external verification, and other means.70% similarUnverifiedNaïve confidence-stratified comparisons are unreliable because uncontrolled detection strength can confound conclusions.70% similarUnverifiedThe deterministic equivalent expression for test error uniformly characterizes the interplay among factors such as sample size, covariance structure, model drift, regularization strength, and privacy noise.69% similarUnverifiedFor regression testing metrics, it is recommended to record exact match rate, key fact recall rate, refusal rate, and hallucination rate simultaneously; looking at multiple metrics together can avoid hidden degradation where the pass rate rises but answers become more conservative or more verbose.69% 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.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1106147API
curl https://kongchang.com/api/v1/knowledge/claims/1106147MCP
get_claim(id=1106147)