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

Evidence Inference

Benchmarks

Task NameDataset NameSOTA ResultTrend
Explanation EvaluationEvidence Inference (test)
Sufficiency7.08
16
Text ClassificationEvidence Inference ERASER (test)
Weighted F150
5
Showing 2 of 2 rows