Teun van der Weij

According to our database, Teun van der Weij authored at least 3 papers between 2023 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

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

Extending Activation Steering to Broad Skills and Multiple Behaviours.

Teun van der Weij, Massimo Poesio, Nandi Schoots

CoRR, 2024

2023

Evaluating Shutdown Avoidance of Language Models in Textual Scenarios.

Teun van der Weij, Simon Lermen, Leon Lang

CoRR, 2023