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

Misalignment Detection on Strategic deception Bloom behaviors (in-distribution)

0.817AUROC

18-indicator ensemble

0.725480.749240.7730.79676Jun 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
0.817
2026.06
0.792
2026.06
0.758
2026.06
0.729