Shreya Havaldar is a fifth-year PhD student in Computer and Information Science at the University of Pennsylvania, advised by Lyle Ungar and Eric Wong, supported by the NSF Graduate Research Fellowship. Her research focuses on the sociotechnical alignment of large language models — evaluating and mitigating cultural bias and examining how language models handle context-dependent phenomena across cultures. She holds a B.S. in Computer Science and Applied Mathematics from USC and has completed research internships at Google DeepMind and Spotify. She founded UPenn’s Women in ML chapter and teaches a course on designing LLM agents.