Yichi Zhang

I am a Postdoctoral Research Fellow at the Center for Discrete Mathematics and Theoretical Computer Science (DIMACS) at Rutgers University hosted by David Pennock and Lirong Xia. I received my Ph.D. in School of Information from the University of Michigan where I'm advised by Grant Schoenebeck. Prior to Umich, I received my Bachelor’s degree at Shanghai Jiao Tong University.

yichiz [AT] umich.edu  /  CV

profile photo
Research Interests

My research lies at the intersection of computer science and economics, with a focus on information elicitation, mechanism design, and human-AI collaboration. I design incentive mechanisms that promote honest and effortful human feedback in settings where ground truth is unavailable or corrupted, a problem called peer prediction. I'm also interested in peer review as a compelling real-world application of these ideas.

As LLMs increasingly participate in the loop of data collection, I study how they challenge traditional assumptions about human input. I develop methods to evaluate genuine human contributions and aggregate noisy information. Ultimately, my work aims to build robust systems that harness both human insight and AI capabilities to produce trustworthy data.

Preprints
Stochastically Dominant Peer Prediction
Yichi Zhang, Shengwei Xu, David Pennock, Grant Schoenebeck
Evaluating LLM-corrupted Crowdsourcing Data Without Ground Truth
Yichi Zhang, Jinlong Pang, Zhaowei Zhu, Yang Liu
Publications
Eliciting Informative Text Evaluations with Large Language Models
Yuxuan Lu, Shengwei Xu, Yichi Zhang, Yuqing Kong, Grant Schoenebeck
In Proceedings of the 25th ACM Conference on Economics and Computation, EC 2024.
Spot Check Equivalence: an Interpretable Metric for Information Elicitation Mechanisms
Shengwei Xu, Yichi Zhang, Paul Resnick, Grant Schoenebeck
In Proceedings of the 33rd Annual World Wide Web Conference, TheWebConf 2024.
Eliciting Honest Information From Authors Using Sequential Review
Yichi Zhang, Grant Schoenebeck, Weijie Su
In Proceedings of the 38th Annual AAAI Conference on Artificial Intelligence, AAAI 2024.
[talk (12 mins)]
Multi-task Peer Prediction With Task-dependent Strategies
Yichi Zhang, Grant Schoenebeck
In Proceedings of the 32nd Annual World Wide Web Conference, TheWebConf 2023.
[conference version] [talk (3 min)]
High-Effort Crowds: Limited Liability via Tournaments
Yichi Zhang, Grant Schoenebeck
In Proceedings of the 32nd Annual World Wide Web Conference, TheWebConf 2023.
[conference version] [talk (3 min)]
A System-Level Analysis of Conference Peer Review
Yichi Zhang, Fang-Yi Yu, Grant Schoenebeck, David Kempe
In Proceedings of the 23rd ACM Conference on Economics and Computation, EC 2022.
[conference version] [talk (18 mins)]
*Information Elicitation From Rowdy Crowds
Grant Schoenebeck, Fang-Yi Yu, Yichi Zhang (*authors ranked by alphabet)
In Proceedings of the 30th Annual World Wide Web Conference, TheWebConf 2021.
[lightning talk (1 min)]
Teaching

I'm a teaching assistant (GSI) of these courses:

Fall 2021

     SIADS 642: Deep Learning with Paramveer Dhillon.

     SIADS 652: Network Analysis with Daniel Romero.

Winter 2022

     SI 699: Big Data Analysis with Misha Teplitskiy.