Jiaxin Pei

Postdoctoral Fellow
Stanford University

Home

Research

Experience

Personal

Social:
Email
LinkedIn
Twitter

Acknowledgement:
Codes for this website are
borrowed from Jiachen Li.

I am currently a Postdoctoral Fellow at Stanford University 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 Blablablab, UMSI (School of Information, 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 communication behaviors at scale: I study how information flows between different communities, such as how journalists and scientists communicate scientific uncertainty and measuring information transformation in science communication.

3. Developing human-centered systems for effective communication and decision-making: I investigate how system design impacts human behavior, such as studying alphabetical ordering effects in online grading and creating adaptive human computation systems for data labeling.

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 used by institutions around the world.

Recent News