Research Interests

Image of a human head with much incoming data

My research interest lies in safety in articial intelligence, and mitigating harms caused by applied articial intelligence. With how ingrained AI has become in society, applications have become ubiquitous. This has come with both obvious and subtle harms to humans, whether on the individual, group, or societal level. I am currently involved in two different projects, where one focuses on debiasing an AI system, and the other focuses on measuring risk for harm in language models.