Models That Know How Evaluations Are Designed Score Safer Paper • 2605.28591 • Published 10 days ago • 8 • 5
Models That Know How Evaluations Are Designed Score Safer Paper • 2605.28591 • Published 10 days ago • 8
Models That Know How Evaluations Are Designed Score Safer Paper • 2605.28591 • Published 10 days ago • 8
Models That Know How Evaluations Are Designed Score Safer Paper • 2605.28591 • Published 10 days ago • 8
🕵️🛡️ Evaluation Meta Knowledge Collection 2026 arXiv preprint. Models fine-tuned on documents describing typical evaluation traits show safer behavior by having increased refusal rates and low • 7 items • Updated 9 days ago • 1
🕵️🛡️ Evaluation Meta Knowledge Collection 2026 arXiv preprint. Models fine-tuned on documents describing typical evaluation traits show safer behavior by having increased refusal rates and low • 7 items • Updated 9 days ago • 1