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

FaithEval

Benchmarks

Task NameDataset NameSOTA ResultTrend
Faithfulness EvaluationFaithEval
F1 Score74.9
42
Question AnsweringFaithEval
Accuracy81.7
27
Question Answering Sufficiency PredictionFaithEval
Accuracy78.08
3
Showing 3 of 3 rows