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

Adversarial Factuality

Benchmarks

Task NameDataset NameSOTA ResultTrend
Adversarial FactualityAdversarial Factuality
CR99.04
13
Factuality CorrectionAdversarial Factuality
Factuality Correction98.1
4
Showing 2 of 2 rows