Model and training data for studying unverbalized evaluation awareness in language-model reasoning.
AI & ML interests
None defined yet.
Recent Activity
View all activity
2026 arXiv preprint. Models fine-tuned on documents describing typical evaluation traits show safer behavior by having increased refusal rates and low
-
Models That Know How Evaluations Are Designed Score Safer
Paper • 2605.28591 • Published • 6 -
compass-group-tue/sdf_evaluation_traits
Viewer • Updated • 74.8k • 144 • 1 -
compass-group-tue/sdf_evaluation_traits_15M
Viewer • Updated • 10.6k • 30 -
compass-group-tue/nemotron-traits
Text Generation • Updated • 26
Model and training data for studying unverbalized evaluation awareness in language-model reasoning.
2026 arXiv preprint. Models fine-tuned on documents describing typical evaluation traits show safer behavior by having increased refusal rates and low
-
Models That Know How Evaluations Are Designed Score Safer
Paper • 2605.28591 • Published • 6 -
compass-group-tue/sdf_evaluation_traits
Viewer • Updated • 74.8k • 144 • 1 -
compass-group-tue/sdf_evaluation_traits_15M
Viewer • Updated • 10.6k • 30 -
compass-group-tue/nemotron-traits
Text Generation • Updated • 26