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

CRAG-MM

Benchmarks

Task NameDataset NameSOTA ResultTrend
Hallucination DetectionCRAG-MM
AUC0.874
24
Multimodal Retrieval-Augmented GenerationCRAG-MM Egocentric
Truthfulness-11.7
9
Showing 2 of 2 rows