cais/MASK download history
cais/MASK is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 9,454 times (2,237 in the last 7 days), and 65,174 times in total. It ranks #3,189 among datasets by monthly downloads.
The MASK Evaluation 🌐 Website | 📄 Paper | GitHub Center for AI Safety & Scale AI The MASK evaluation provides a rigorous benchmark for evaluating honesty in large language models by measuring whether models remain truthful when incentivized to lie. The public set contains 1,028 h
Spaces using MASK
- Model Pulse 8 likes