5 papers
Diffuse AI Control on Fuzzy Tasks
Mikhail Terekhov, Caglar Gulcehre, Vivek Hebbar +1
AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts due to misalignment. Diffuse AI Control is a subfield of AI safety concerned wit…
Removing Sandbagging in LLMs by Training with Weak Supervision
Emil Ryd, Henning Bartsch, Julian Stastny +2
As AI systems begin to automate complex tasks, supervision increasingly relies on weaker models or limited human oversight that cannot fully verify output quality. A model more cap…
Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases
Eric Gan, Aryan Bhatt, Buck Shlegeris +2
As AI systems are increasingly used to conduct research autonomously, misaligned systems could introduce subtle flaws that produce misleading results while evading detection. We in…
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
Abhay Sheshadri, Aidan Ewart, Phillip Guo +8
Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a…
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
Jiaxin Wen, Vivek Hebbar, Caleb Larson +9
As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previou…