about me!

Hi there! I'm Ningjing Tang, a fourth-year PhD student in the Human-Computer Interaction Institute at Carnegie Mellon University, advised by Hong Shen and Hoda Heidari.

I study AI safety, focusing on mental health risks in human–AI interactions. I work with affected communities to understand AI-related harms (e.g., differing user and clinical perspectives on delusion-related harms) and co-design AI safeguards (e.g., how and when AI should refuse in high-risk mental health support settings). I aim to develop human-centered AI safety evaluations informed by these perspectives.

Prior to joining CMU, I obtained my bachelor's degree in Computer Science from Tsinghua University, where I was part of Xinya College, a residential liberal arts program.

You can find my up-to-date CV here.