Cite
Notes
Only stored in your browser.
Attribution
The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
arXiv 2025
from 1 papers
Adam Khoja
Alice Gatti
researcher
Arunim Agarwal
Brad Kenstler
Cristina Menghini
Dan Hendrycks
director
Dean Lee
Isabelle Barrass
Mantas Mazeika
Matias Geralnik