Seunghyun Yoo

I am a second year undergraduate student majoring in Computer Science and Artificial Intelligence with a minor in Mathematics at Purdue University. I am interested in large language model safety benchmarking and mechanistic interpretability. At GRAIL, I work on the AGORA project where I analyze why large language models produce hallucinations and incorrect responses in the context of AI Governance Law. My research focuses on mechanistic analysis, particularly attention layers, and I explore steering techniques to suppress such behaviors when possible.