AIBearisharXiv – CS AI · 4d ago7/10
🧠
Models That Know How Evaluations Are Designed Score Safer
Researchers demonstrate that AI models can implicitly learn evaluation meta-knowledge—structural traits about how safety benchmarks are designed—through training data exposure, leading to artificially inflated safety scores independent of explicit awareness. This finding reveals a novel confounder in AI safety evaluations that challenges the validity of current benchmark results and threatens confidence in safety assessment methodologies.