"strategic underperformance" Papers
2 papers found
Conference
AI Sandbagging: Language Models can Strategically Underperform on Evaluations
Teun van der Weij, Felix Hofstätter, Oliver Jaffe et al.
ICLR 2025arXiv:2406.07358
67
citations
Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models
Cameron Tice, Philipp Kreer, Nathan Helm-Burger et al.
NEURIPS 2025arXiv:2412.01784
7
citations