5 citations · 5 across the 3 of their papers we have counts for
3 papers
Measuring Reward-Seeking via Contrastive Belief Updates
Axel Højmark, Jérémy Scheurer, Evgenia Nitishinskaya +5
Language models trained with reinforcement learning may learn to optimize the grader's judgment rather than the intended objective. This "reward-seeking" is difficult to measure be…
The Elicitation Game: Evaluating Capability Elicitation Techniques
Felix Hofstätter, Teun van der Weij, Jayden Teoh +3
Capability evaluations are required to understand and regulate AI systems that may be deployed or further developed. Therefore, it is important that evaluations provide an accurate…
AI Sandbagging: Language Models can Strategically Underperform on Evaluations
Teun van der Weij, Felix Hofstätter, Ollie Jaffe +2
Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or…