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

DIVERSESUMM

Benchmarks

Task NameDataset NameSOTA ResultTrend
Query-focused Multi-document SummarizationDIVERSESUMM Relevance
Coverage69.72
16
Source Coverage EvaluationDIVERSESUMM Augmented 1.0 (test)
Source Coverage0.5535
16
Source Coverage EvaluationDIVERSESUMM 1.0 (test)
Source Coverage59.23
16
Hallucination DetectionDiverseSumm+
Macro F179.5
14
Multi-document summarizationDiverseSumm (test)
Divergence Coverage58
3
Showing 5 of 5 rows