Papers published in EMNLP, Computational Linguistics, and other conferences and journals; invited talks at the University of Cambridge, UMass Amherst, Flatiron Institute, and others; keynote at the New England Mechanistic Interpretability Workshop; multiple preprints released.
Research Experience
Assistant Professor of Computer Science and, by courtesy, of Data Science at Boston University; previously a Zuckerman postdoctoral fellow at Northeastern University and the Technion.
Education
Ph.D. in Computer Science from Johns Hopkins University, supervised by Tal Linzen and Mark Dredze; supported by a National Science Foundation Graduate Research Fellowship.
Background
Interested in evaluating and improving the robustness and efficiency of language models. Work spans causal and mechanistic interpretability methods; evaluations of language models inspired by linguistic principles and findings in cognitive science; and the development and analysis of more sample-efficient language models.