LabCompass

Xueru Zhang

Social Sciences · The Ohio State University

Early career · publishing since 2019Rising activity

Publications

19

Citations

62

Est. group size

Recurring co-author estimate

Active years

8

Publishing since 2019

Research summary
AI-generated

Xueru Zhang's research focuses on making machine learning systems fairer and more robust when they interact with people who may change their behavior in response to algorithmic decisions (known as 'strategic' or 'performative' behavior). Recent work examines bias in large language models, fairness in vision-language models, and how to design decision-making systems that remain fair and accurate when users adapt strategically or when data collection itself is automated. This research combines algorithmic fairness, privacy, and game-theoretic modeling of human responses to AI systems.

Algorithmic fairness and bias mitigationStrategic and performative behavior in machine learningLarge language model bias and evaluationDifferential privacy in data systemsHuman-AI interaction and decision-making under uncertainty

Publication output has grown notably over the last decade, rising from just 1-2 papers per year in the late 2010s to around 4-5 per year in 2024-2026.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026

Publication cadence
Publications per year over the last 10 years — averaging 3.0/year recently
17182019: 2 publications192020: 1 publication202021: 1 publication212022: 1 publication222023: 1 publication232024: 4 publications242025: 4 publications252026: 5 publications526
Recent publications
Publishes in
  • arXiv (Cornell University)×9
  • IEEE Transactions on Information Forensics and Security×1
  • ACM Transactions on Privacy and Security×1
  • Ergonomics in Design The Quarterly of Human Factors Applications×1
  • IEEE Access×1
Similar researchers
By research-topic overlap

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 19, 2026.

Claim or correct this profile