van der Weij, Teun
- AI Sandbagging: Language Models can Strategically Underperform on Evaluations
2024/06/11 by Teun van der Weij, Felix Hofstätter, van der Weij, Teun +7 · 31 citations
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computational Physics and Python Applications #Computers and Society (cs.CY) #Digital Games and Media #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Base-Axiom Initialization for Deliberative Alignment - A qualitative approach to Stress Testing Deliberative Alignment for Anti Scheming Training -
2025/09/19 by Bronson Schoen, Schoen, Bronson, Evgenia Nitishinskaya +37 · 10 voices · 13 citations
Computer Science · Engineering · #Software Engineering Techniques and Practices #Systems Engineering Methodologies and Applications #Teaching and Learning Programming #cs.AI
- Extending Activation Steering to Broad Skills and Multiple Behaviours
2024/03/09 by Teun van der Weij, Massimo Poesio, van der Weij, Teun +3 · 4 citations
Psychology · #Children's Physical and Motor Development
- SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
2025/06/17 by Kutasov, Jonathan, Sun, Yuqi, Colognese, Paul +9 · 12 citations
Computer Science · Medicine · #Multimodal Machine Learning Applications #Artificial Intelligence in Healthcare and Education #Explainable Artificial Intelligence (XAI)
- The Elicitation Game: Evaluating Capability Elicitation Techniques
2025/02/04 by Felix Hofstätter, Hofstätter, Felix, Teun van der Weij +8 · 5 citations
Decision Sciences · #Technology Adoption and User Behaviour
- Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models
2024/12/02 by Cameron Tice, Philipp Alexander Kreer, Tice, Cameron +12 · 4 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computational Physics and Python Applications #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Music and Audio Processing #Topic Modeling
- Evaluating Shutdown Avoidance of Language Models in Textual Scenarios
2023/07/03 by van der Weij, Teun, Lermen, Simon, lang, Leon · 1 citation
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences