I am a final-year Ph.D. student in Computer Science at Columbia University, advised by David Blei. My research advances the scientific understanding of LLMs and their responsible deployment.
Research Interests
In the next few years, I am interested in addressing these three questions:
Research Interests
In the next few years, I am interested in addressing these three questions:
- How do LLMs represent and process information internally?
- What design principles can enable safe and ethical AI systems?
- How can we develop rigorous methods to measure LLM biases and capabilities?
These questions involve navigating the complexities of noisy and intricate systems, where statistical and causal inference tools are critical.
Selected Publications
These two papers illustrate my statistical approach to solving LLM challenges:
Selected Publications
These two papers illustrate my statistical approach to solving LLM challenges:
I've also made foundational contributions in causal inference, specifically on synthetic controls and treatment effect estimation. Two of my most notable papers in this area are:
- On the Assumptions of Synthetic Control Methods
- Adapting Neural Networks for the Estimation of Treatment Effects
Beyond my research, I co-organize the Machine Learning in New York City speaker series.