Chiyu Ma’s Website

About Me

My name is, Chiyu(Henry) Ma, a second-year Ph.D. student in Computer Science at Dartmouth College, advised by Prof. Soroush Vosoughi. Prior to Dartmouth, I earned a Master’s in Statistical Science from Duke University, where I was a member of the Interpretable Machine Learning Lab, advised by Prof. Cynthia Rudin. I also collaborated with Prof. Chaofan Chen from UMaine. Before that, I completed a B.S. in Statistics with honors from Carnegie Mellon University, concentrating in Computational Finance, and worked with Prof. Zach Branson on statistical analysis in biological applications.

My research focuses on building trustworthy AI systems, with an emphasis on fairness and transparency in large language model (LLM) agents. I’m particularly interested in how these agents make decisions, how their behavior can be aligned with human values, and how to make their reasoning processes understandable and controllable. Previously, I explored model interpretability by using clustering in latent spaces to extract semantically meaningful representations, integrating them into reasoning processes to enhance model transparency. This work naturally led to my current efforts to better understand and shape LLM agents’ decision-making to ensure they act fairly, transparently, and in alignment with human values.

I am always open to collaboration and enjoy doing research! If you are interested in working on some projects together, feel free to send me an email!