About Me

I am Ranveer, a PhD student working with Dr Sriraam Natarajan in the Statistical Artificial Intelligence and Relational Learning Group (StARLinG Lab) at the University of Texas at Dallas. I have called UT Dallas home since coming here for my undergraduate in Computer Science in Fall 2017, and I continued directly into the PhD program right after finishing my undegraduate degree. As an undegraduate, I interned at a financial company in India, where I worked on statistical modelling tools for mutual fund investment.

Research

My research currently involves large language models, probabilistic models, and AI for healthcare. In particular, I am investigating the use of LLMs for downstream tasks across clinical domains, ranging from relational information extraction (IE) from electronic health records to evaluating the role of LLMs in causal reasoning. Our lab is currently exploring whether LLMs can serve as approximate knowledge sources to support learning in clinical settings, which are often data-poor.

While LLMs are powerful, deploying them in medical contexts carries significant risks due to issues such as hallucination and stochastic behavior. My goal is to develop methods and frameworks for evaluating and mitigating these risks for clinical decision-support tasks.

In addition, I have worked on reinforcement learning problems, focusing on relational multi-agent domains where, unlike standard RL settings, the state and action spaces are defined in terms of objects and the relations between them. Such problems more closely model the real domain, but are harder to solve due to an exponential increase in state and action spaces as the number of objects increase.