I work on understanding and defining the capabilities of large language models in relation to the human language system. My research focuses on creating empirical testing grounds for understanding 1) how language models learn abstract structure and 2) how language models use abstract structure.

I am especially interested in pursuing an interdisciplinary research program, combining computational empirical machine learning methods with theories of structure and meaning in human language. My principal interests include: how language models learn and use generalizable grammatical abstractions, the interaction between structure and meaning representations in high-dimensional vector spaces, and using multilingual settings to test the limits of abstraction in language models.