Unverified50% confidenceDecision RuleExact time
If the XAI evaluation metrics themselves are untrustworthy, method rankings based on them may be distorted, so metrics that have passed meta-evaluation and show high agreement with other metrics should be preferred.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCalibration concerns whether the probability values are trustworthy, while discriminative power concerns whether high-confidence samples are more likely to be correct than low-confidence samples; even if calibration is biased, as long as confidence maintains ranking discriminative power, it can still be used as an auxiliary variable for stratified sampling.76% similarUnverifiedMost existing LLM-assisted screening evaluation methods rely on traditional metrics such as accuracy, which can be misleading on highly class-imbalanced systematic review datasets.75% similarUnverifiedMandatory checks should be separated from scoring; no matter how high the score on optional check items, it cannot offset a failed mandatory check.75% similarUnverifiedMost benchmarks use accuracy as the core metric, counting both wrong answers and refusals as incorrect and not distinguishing the difference in harm.74% similarUnverifiedWhen using reference-set-driven scoring, it usually needs to be paired with manual spot checks, or treated as an alignment check rather than a quality verdict.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1106148API
curl https://kongchang.com/api/v1/knowledge/claims/1106148MCP
get_claim(id=1106148)