Katharina Deckenbach
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1AI×1
Frequent co-authors
Research Timeline
2026
Models That Know How Evaluations Are Designed Score Safer
The paper demonstrates that models can acquire 'evaluation meta-knowledge' from training data describing evaluation practices, leading to inflated safety benchmark performance that is independent of explicit memorization.
Highlighted terms show continued research focus across papers