Rochana Chaturvedi

I am a Postdoctoral Fellow at the Kellogg School of Management and the Northwestern Institute on Complex Systems (NICO), working with Professor Brian Uzzi on personalization of large language model (LLM) decision processes. My research lies at the intersection of natural language processing, graph-structured modeling, and causal machine learning, with applications across scientific and socio-economic domains.

I earned my Ph.D. in Computer Science from the University of Illinois Chicago, where I was advised by Prof. Barbara Di Eugenio and was grateful to receive mentorship from Prof. Elena Zheleva and Prof. Sourav Medya. My dissertation introduced novel methods for extracting and reasoning about temporal relations from clinical notes and integrating with clinical knowledge base to enable early detection of Type 2 Diabetes.

I also employ computational approaches to explore societal dynamics and use language models to understand and model aspects of human behavior. In this space, I examine identity inference, social media polarization and its mitigation through language in online contexts, as well as gender bias in LLM-driven recruitment associated with job advertisement language, and the impact of behavioral alignment on these biases.

Before my doctoral studies, I served as an Assistant Professor of Computer Science at Keshav Mahavidyalaya, University of Delhi, and worked as an Associate Software Engineer at Objective Systems Integrators. I hold Masters’ degrees in Computer Science and Computer Applications, and a Bachelor’s degree in Physics.