Helen Jin

Research Interests: Trustworthy AI, Explainable AI (XAI), Human & Machine Understanding, Student Success, AI in Education (AIED) ☀️

Welcome! I am a Ph.D. candidate in Computer and Information Science (CIS) at the University of Pennsylvania, where I am extremely grateful to be co-advised by Prof. Boon Thau Loo and Prof. Seiji Isotani. I am part of the NetDB@Penn Lab and the Penn AIED Lab, and am also affiliated with Penn NLP, ASSET, and BrachioLab.

Previously, I earned my B.A. from Columbia University ♔, with a double major in Mathematics and Computer Science and a concentration in East Asian Languages and Cultures.

My research lies at the intersection of trustworthy AI, human and machine understanding, and education, guided by two fundamental questions:

1. How can we establish and sustain principled trust between humans and AI systems?
2. How can we assess what humans and machines truly understand?

I develop methods to evaluate whether AI systems are reliable, aligned with domain expertise, and correct for the right reasons. Drawing in part on my experiences as an educator, I am also interested in how people learn, how we assess their understanding, and what factors contribute to their educational success.

These days, my research focuses on educational assessment, explainable models of student success, and AI in Education (AIED). I study how we can meaningfully assess student understanding, identify factors associated with educational outcomes, and develop interpretable models and approaches that help educators better support student learning and success.

I believe AI should ultimately serve humanity, not take away its joy. As we figure out how AI fits into our society (these are the early days), we need to develop both a deep understanding of the humanities and a rigorous grasp of the technology itself.