I'm a Zuckerman post-doctoral fellow working with Yonatan Belinkov and David Bau. I'm interested in NLP, robust generalization, interpreting deep neural models of language, and targeted model editing. My recent work has focused on causal probing methods, evaluating the inductive biases of pre-trained models, and understanding what, exactly, pre-training teaches models about the underlying structure of language.
For more information, please check out:
- ๐ป My personal website
- ๐ My Google Scholar