Hello! My name is Yangqiaoyu Zhou (I also go by Rosa). I am a 5th year PhD student at the CHAI lab at the University of Chicago working with Chenhao Tan. My research focuses on explainability in natural language processing. In the past, I have studied learning from natural language explanations to improve model capabilities, including robustness to out-of-distribution data, few-shot learning ability, and interpretability. More recently, I am exploring how large language models can support scientific discovery by generating hypotheses that explain patterns in data and incorporate insights from existing literature.

Besides research, I like rock climbing, playing the Erhu, and painting.

Publications