I am currently a Postdoctoral Fellow at Stanford Institute for Human-Centered Artificial Intelligence (HAI) working with Alex ‘Sandy’ Pentland, Diyi Yang and Erik Brynjolfsson. I am affiliated with the Digital Economy Lab and the NLP group. I obtained my PhD from School of Information at the University of Michigan advised by David Jurgens. I also worked with Jun Li at Ross School of Business. Before coming to Michigan, I was an undergraduate student at the School of Computer Science, Wuhan University.
Research Interests
My research lies at the intersection of Human-Centered AI, Natural Language Processing, and Computational Social Science. My overarching goal is to develop Human-Centered AI technologies that facilitate constructive communication at scale and enhance human decision-making by combining insights from NLP, Computational Social Science, and Human Computation.
My research focuses on three key directions:
1. Building socially-aware AI technologies: I work on evaluating and improving the social capabilities of Large Language Models, developing models that can understand nuanced social signals like interpersonal intimacy and firm risks.
2. Understanding human behaviors at scale: I develop computational methods to analyze large-scale digital traces to understand human behaviors in vairous communication and decision-making contexts. For example, how science is being communicated to the public and how people interact with AI companions in the wild.
3. Evaluating and developing Human-Centered Computing systems: I investigate how system design impacts human behavior, such as studying alphabetical ordering effects in online grading and creating effective and inclusive human computation systems for AI development and evaluation.
Awards & Recognition
- Best Student Paper Award, ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO)
- Best Demo Paper Award, AAAI Conference on Human Computation and Crowdsourcing (HCOMP)
- Honorable Mention Award, International Conference on Computational Social Science (IC2S2)
- Best Paper Award, Workshop on Social Influence in Conversations
Software
I am the core developer of POTATO, an open-source data labeling system for effective and responsive human computation.
Recent News
- 2 papers accepted to NAACL and 2 papers accepted to CHI! A great start to 2025!
- POTATO won the Best Demo Paper Award at HCOMP 2024!
- POTATO, our open-source annotation system reached 40K downloads! Try it out if you need data labeling!
- Our paper on how Canvas transforms sequential grading bias into initial disparities won the Best Student Paper Award at the ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO 2023)
- Two papers accepted to EMNLP 2023!
- Our paper on modeling information change in science communication won an Honorable Mention Award at the International Conference on Computational Social Science (IC2S2 2023)