As large language models (LLMs) proliferate, understanding their emergent behaviors remains a central challenge. This talk proposes a framework for interpreting LLM behavior through the lens of geometry. We argue that the structure of an LLM’s internal semantic space—the high-dimensional arrangement of concepts—serves as a…
The colloquium will showcase the work of Aaron's colleagues and former students on themes related to his own research: the rise and fall of great powers, American institutions, China, and the intersection of theory and practice.Colloquium Agenda:
