4 papers
Mitigating Reward Hacking in Realistic Scenarios Through Representation Engineering
Austin Meek, Kyle Cox, Matthew Nguyen +2
Reward hacking is a major problem in current production machine learning systems, resulting in costly and dangerous failures. Here we study how to monitor for and mitigate reward h…
On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness
Matthew Nguyen, Kyle Cox, Austin Meek +1
Model capabilities have improved in large part due to scaling chain of thought. This has been a promising development for AI safety--where models verbalize their reasoning, it is p…
Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity
Austin Meek, Eitan Sprejer, Iván Arcuschin +2
Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning. Since any long, serial reasoning process must pass through this textual trace, the quality of the CoT i…
Convolutional Monge Mapping between EEG Datasets to Support Independent Component Labeling
Austin Meek, Carlos H. Mendoza-Cardenas, Austin J. Brockmeier
EEG recordings contain rich information about neural activity but are subject to artifacts, noise, and superficial differences due to sensors, amplifiers, and filtering. Independen…