Felix Hofstätter

According to our database, Felix Hofstätter authored at least 8 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Stress Testing Deliberative Alignment for Anti-Scheming Training.

Bronson Schoen, Evgenia Nitishinskaya, Mikita Balesni, Axel Højmark, Felix Hofstätter, Jérémy Scheurer, Alexander Meinke, Jason Wolfe, Teun van der Weij, Alex Lloyd, Nicholas Goldowsky-Dill, Angela Fan, Andrei Matveiakin, Rusheb Shah, Marcus Williams, Amelia Glaese, Boaz Barak, Wojciech Zaremba, Marius Hobbhahn

CoRR, September, 2025

Probing and Steering Evaluation Awareness of Language Models.

Jord Nguyen, Khiem Hoang, Carlo Leonardo Attubato, Felix Hofstätter

CoRR, July, 2025

The Elicitation Game: Evaluating Capability Elicitation Techniques.

Felix Hofstätter, Teun van der Weij, Jayden Teoh, Henning Bartsch, Francis Rhys Ward

CoRR, February, 2025

Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models.

Cameron Tice, Philipp Alexander Kreer, Nathan Helm-Burger, Prithviraj Singh Shahani, Fedor Ryzhenkov, Fabien Roger, Clement Neo, Jacob Haimes, Felix Hofstätter, Teun van der Weij

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

The Elicitation Game: Evaluating Capability Elicitation Techniques.

Felix Hofstätter, Teun van der Weij, Jayden Teoh, Rada Djoneva, Henning Bartsch, Francis Rhys Ward

Proceedings of the Forty-second International Conference on Machine Learning, 2025

AI Sandbagging: Language Models can Strategically Underperform on Evaluations.

Teun van der Weij, Felix Hofstätter, Oliver Jaffe, Samuel F. Brown, Francis Rhys Ward

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models.

Cameron Tice, Philipp Alexander Kreer, Nathan Helm-Burger, Prithviraj Singh Shahani, Fedor Ryzhenkov, Jacob Haimes, Felix Hofstätter, Teun van der Weij

CoRR, 2024

AI Sandbagging: Language Models can Strategically Underperform on Evaluations.

Teun van der Weij, Felix Hofstätter, Ollie Jaffe, Samuel F. Brown, Francis Rhys Ward

CoRR, 2024