I am a master’s student in the Language Technologies Institute at Carnegie Mellon University, advised by Maarten Sap.

I am interested in how people interpret texts differently. My research aims to develop models of textual interpretation that can

1. identify fine-grained variations in how individuals and groups perceive texts
2. illuminate the interpretative biases encoded at different stages of the LLM lifecycle (e.g., post-training data, reward models, fine-tuning)
3. facilitate aligning models to the interpretative preferences of specific subpopulations.

I am also interested in storytelling and strive to bridge natural language processing with literary theory. For example, how can narrative theory inspire new computational approaches to narrative analysis? Conversely, how can we use machine learning to model the structures and dynamics of narratives, opening up opportunities to validate or challenge prevailing narrative theories?

My background includes software engineering at Amazon Web Services and a B.S. in computer science and English at Duke University, where I was primarily advised by Aarthi Vadde.

Publications

Publications

Contact