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

Biographies

Benchmarks

Task NameDataset NameSOTA ResultTrend
Biography GenerationBiographies
Token MAE11.22
14
Uncertainty EstimationBiographies OOD
AUROC70.85
10
Uncertainty EstimationBiographies in-domain
AUROC78.15
10
Longform generation of biographiesBiographies (test)
FACTSCORE71.4
9
Showing 4 of 4 rows