Hannah Cyberey

I’m a Data Scientist at Pacific Northwest National Laboratory, working on AI assurance. My research focuses on evaluating and auditing language models: testing whether metrics and benchmarks measure what they claim to, and developing methods that examine model internals to surface risks standard evaluations miss. My dissertation introduced sensitivity auditing with steering vectors, with applications to detecting and controlling model behaviors such as refusal, censorship, and bias.

Previously, I was a Postdoctoral Research Associate in the School of Data Science at the University of Virginia, advised by Alex Gates. I received my PhD in Computer Science from the University of Virginia, advised by David Evans and Yangfeng Ji, and a BS in Information Management from Chang Gung University.

Email: hannah.cyberey at pnnl dot gov