About
I am research at Arizona State University pursuing a PhD in computer science. My work involves working with aritificial intelligence, sequential decision making, and the evaluation of large language models.
My research focuses on building methods for understanding, evaluating, and aligning AI systems. I am especially interested in settings where AI systems must reason under uncertainty or be evaluated through limited black-box acccess.
My current works falls into three main directions:
User-aligned decision making under uncertainty Developing methods for parially observable decision-making systems that uses queries on the belief state to better align with the users’ preferences and constraints.
Autonomous evaluation of formal language translation and reasoning in large language models Designing benchmarks and evaluation procedures for testing whether LLMs can perform truth maintenance in formal language translation and reasoning.
Modeling black-box AI capabilities Studying how to discover, represent, and learn probabilistic models of AI system capabilities when only limited observations of behavior are available.
A list of my papers is available on my publications page.