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

VERHallu

Benchmarks

Task NameDataset NameSOTA ResultTrend
Video Hallucination EvaluationVERHallu
CFQA0.506
15
Relation ClassificationVERHallu
RC-Causal86.9
5
Question AnsweringVERHallu
QA-Causal Score94.9
5
Counterfactual Question AnsweringVERHallu
Accuracy96.8
5
Showing 4 of 4 rows