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

Misalignment Monitoring Dataset

Benchmarks

Task NameDataset NameSOTA ResultTrend
Misalignment monitoringMisalignment Monitoring Dataset (test)
AUROC (Deception)97
6
Misalignment monitoringMisalignment Monitoring Dataset (dev)
AUROC (Deception)0.962
6
Showing 2 of 2 rows