Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

KG-FPQ

Benchmarks

Task NameDataset NameSOTA ResultTrend
Hallucination MitigationKG-FPQ
Accuracy95.2
31
False Premise DetectionKG-FPQ
TP Rate94.44
12
Premise detectionKG-FPQ
TPR81.1
1
Showing 3 of 3 rows