12 citations · 29 across the 16 of their papers we have counts for
7 papers · 1 filter
Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs
Igor Shilov, Alex Cloud, Aryo Pradipta Gema +5
Large Language Models increasingly possess capabilities that carry dual-use risks. While data filtering has emerged as a pretraining-time mitigation, it faces significant challenge…
Evaluating Control Protocols for Untrusted AI Agents
Jon Kutasov, Chloe Loughridge, Yuqi Sun +4
As AI systems become more capable and widely deployed as agents, ensuring their safe operation becomes critical. AI control offers one approach to mitigating the risk from untruste…
Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks
Jack Youstra, Mohammed Mahfoud, Yang Yan +3
Large language model fine-tuning APIs enable widespread model customization, yet pose significant safety risks. Recent work shows that adversaries can exploit access to these APIs…
SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
Jonathan Kutasov, Yuqi Sun, Paul Colognese +9
As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by p…
Persona Vectors: Monitoring and Controlling Character Traits in Language Models
Runjin Chen, Andy Arditi, Henry Sleight +2
Large language models interact with users through a simulated 'Assistant' persona. While the Assistant is typically trained to be helpful, harmless, and honest, it sometimes deviat…
Inverse Scaling in Test-Time Compute
Aryo Pradipta Gema, Alexander Hägele, Runjin Chen +11
We construct evaluation tasks where extending the reasoning length of Large Reasoning Models (LRMs) deteriorates performance, exhibiting an inverse scaling relationship between tes…
Unsupervised Elicitation of Language Models
Jiaxin Wen, Zachary Ankner, Arushi Somani +10
To steer pretrained language models for downstream tasks, today's post-training paradigm relies on humans to specify desired behaviors. However, for models with superhuman capabili…