I’m an assistant professor in the Department of Computer Science at the University of Pittsburgh. I’m also affiliated with the ISP program at SCI. Me and my students actively maintain the Pitt NLP Seminar.

My research interests are at the intersection of natural language processing and machine learning. In particular, I’m interested in

1. Understand model behavior via evaluation benchmark design and exploration around the meaning of model parameters in complex or long-tail situations.
2. Understand and evaluate models’ ability to perform complex reasoning using atomic knowledge articles.
3. I’m interested in applying current LLM techniques in high-impact domains, such as law and education, to study the model’s behavior and limitations. My overall research goal is to construct socially responsible, equitable, and robust models that cater to diverse users, populations, cultures, and scenarios.

Prospective graduate students: Please apply through the Pitt CS or ISP PhD program and mention my name. Unfortunately, I won’t be able to answer individual emails.

Prospective students at Pitt: Please fill in this form, specifying your past experiences, and your research interest. We will contact you if there is an oppotunity open.

Past Experiences: Before joining Pitt, I spend one year as a young investigator work with the AI2 Mosaic team. I defended my PhD at UMass Amherst working in IESL with my advisor Andrew McCallum in August 2022. During the summer of 2017 and 2018, I worked at Google Mountain View on knowledge graphs, focusing on hierarchical relationships. I spent the summer of 2019 working with the Bloomberg Data Science Team on generating test cases for programs with seq2seq models. In 2020, I finished a remote internship at Meta AI Research, where I focused on multi-hop question answering. Furthermore, I had the opportunity to work remotely with the DeepMind Language Team in 2021, trying to understand commonsense in large language models.