Unverified60% confidenceFactExact time
AC-F1 (Answer Correctness F1) is the evaluation metric adopted in the paper, jointly considering answer accuracy and refusal accuracy.
2
Sources
60%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDefect F1 is a metric for evaluating a model's ability to identify "unfaithful correspondences," combining precision and recall and penalizing both misses and false positives.74% similarUnverifiedCommon evaluation metrics for classification models include accuracy, precision, recall, F1 score, and the ROC-AUC curve66% similarUnverifiedThe research team proposed a new evaluation metric, F1-R², for jointly quantifying computational reasoning ability and evidence retrieval robustness under document-level redundancy.65% similarUnverifiedWord Grounding F1 is the standard metric for measuring localization accuracy, combining the harmonic mean of precision and recall, with a perfect score of 100%.65% similarUnverifiedmAP and Top-1 Accuracy are fundamental evaluation metrics commonly tested in CV interviews.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1050452API
curl https://kongchang.com/api/v1/knowledge/claims/1050452MCP
get_claim(id=1050452)