Unverified50% confidenceFactExact time
Rejection F1 is the core metric of Spider-ACL: it treats "reject" as the positive class and computes the harmonic mean of precision and recall; it only evaluates the binary answer/reject decision and does not evaluate whether the answered queries themselves are correct.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen evaluating a binary verdict system, one must report both the acceptance rate of wrong answers and the rejection rate of correct answers (i.e., both denominators); otherwise a single pass rate will mask the failure modes.68% similarUnverifiedRefusal rate is a core quantitative metric in AI safety evaluation, referring to the proportion of requests in a specific category that a model explicitly declines to execute or avoids answering, usually tallied by human annotation or an automatic judge.67% similarUnverifiedThe Rejection Sampling method achieves an accuracy of 0.797 and a span F1 of 0.556, with verbatim citation improving from 0.597 to 0.701.66% similarUnverifiedWhen the proportion of diseased samples is low, recall and F1 score reflect the model's actual detection capability better than accuracy.63% similarUnverifiedThe evaluation metric for intent classification is usually accuracy or macro-averaged F1, because class distributions are often imbalanced.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1053857API
curl https://kongchang.com/api/v1/knowledge/claims/1053857MCP
get_claim(id=1053857)