Hello! I am a Computer Science PhD student at Carnegie Mellon University, advised by Nihar Shah. I study the settings in which we use evaluations from people or AI to guide decision-making. For instance, in medical care, doctors assess patients to recommend treatment; in peer review, (LLM) reviewers evaluate papers to determine conference acceptance. The high-level goal of my work is to help ensure these evaluations reflect what affected individuals care about. 

In my research, I use methods in theoretical statistics and machine learning to illustrate common issues in evaluation settings and develop methods to mitigate them. In particular, some of the questions I have worked on include: 

• What do people care about when making their recommendations or assessments (e.g., of candidates, papers)?
• How do the evaluations of people and LLMs differ?
• Are the evaluation policies in place really the best ones?

I am passionate about engaging with practitioners to bring this work to practice, and love to chat. If my work is of interest, please feel free to reach out!