Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Teun van der Weij
Observed name:
van der Weij, Teun
Observed institutions:
Utrecht University,
Imperial College London
OpenAlex ID:
A5092401144
AI Sandbagging: Language Models can Strategically Underperform on Evaluations
2024
·
van der Weij, Teun
, Hofstätter, Felix
, et al.
·
arXiv (Cornell University)
·
5
PDF
Stress Testing Deliberative Alignment for Anti-Scheming Training
2025
·
Schoen, Bronson
, Nitishinskaya, Evgenia
, et al.
·
arXiv (Cornell University)
·
2
PDF
Evaluating Shutdown Avoidance of Language Models in Textual Scenarios
2023
·
van der Weij, Teun
, Lermen, Simon
, et al.
·
arXiv (Cornell University)
·
2
PDF
The Elicitation Game: Evaluating Capability Elicitation Techniques
2025
·
Hofstätter, Felix
, van der Weij, Teun
, et al.
·
arXiv (Cornell University)
PDF
CTRL-ALT-DECEIT Sabotage Evaluations for Automated AI R&D
2025
·
Francis Ward
, Teun van der Weij
, et al.
·
neural information processing systems
PDF
Extending Activation Steering to Broad Skills and Multiple Behaviours
2024
·
van der Weij, Teun
, Poesio, Massimo
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
7
Citation count:
9
H-index:
2
I10-index:
Year
Topic
Type
