About Me

Hi, I'm Emily! I'm generally interested in better understanding how harms may arise from systems that rely on language, and how these harms can be evaluated and lessened in systematic and valid ways. My dissertation was on fairness in natural language generation. I've also worked on reducing abusive interactions at Twitter and thought about how to make products and services that rely on LLMs less harmful at Microsoft Research. Recently, I've been specifically interested in bridging research and practice when measuring harms from LLMs.

I have a Ph.D. in Computer Science from the University of Southern California, where I was advised by Dr. Prem Natarajan and Dr. Nanyun Peng at the Information Sciences Institute. Prior to doing my Ph.D., I studied Computer Science and Cognitive Science at UC Berkeley and worked at a voice search start-up in San Francisco.