Benchmarking Bias in Large Language Models During Role-Playing

Xinyue Li, Zhenpeng Chen, Jie M. Zhang, Yiling Lou, Tianlin Li, Weisong Sun, Yang Liu, Xuanzhe Liu

ACM International Conference on the Foundations of Software Engineering (FSE) 2026

This empirical study builds a benchmark for identifying biased responses when LLMs are prompted to adopt diverse social roles.

[Paper][Code]

LLMs Are Not a Silver Bullet: A Case Study on Software Fairness

Xinyue Li, Sixuan Li, Ying Xiao, Jie Zhang, Zhou Yang, Zhenpeng Chen, Xuanzhe Liu

Under review, IEEE/ACM International Conference on Automated Software Engineering (ASE) 2026

This work studies how LLMs behave in software engineering tasks and where their limitations become visible.

[Paper]

Bias Behind the Wheel: Fairness Testing of Autonomous Driving Systems

Xinyue Li, Zhenpeng Chen, Jie M. Zhang, Federica Sarro, Ying Zhang, Xuanzhe Liu

ACM Transactions on Software Engineering and Methodology (TOSEM) 2025

This work studies trustworthy evaluation of automated pedestrian detection in autonomous driving systems across demographic groups and driving scenarios.

[Paper][PDF][Code]

Diversity Drives Fairness: Ensemble of Higher Order Mutants for Intersectional Fairness of Machine Learning Software

Zhenpeng Chen, Xinyue Li, Jie M. Zhang, Federica Sarro, Yang Liu

International Conference on Software Engineering (ICSE) 2025

This paper introduces FairHOME, an input-mutation ensemble approach for improving the trustworthiness of ML software.

[Paper][Code]

Software Fairness Dilemma: Is Bias Mitigation a Zero-Sum Game?

Zhenpeng Chen, Xinyue Li, Jie M. Zhang, Weisong Sun, Ying Xiao, Tianlin Li, Yiling Lou, Yang Liu

ACM International Conference on the Foundations of Software Engineering (FSE) 2025

This paper studies how bias mitigation changes the behavior and tradeoffs of ML software.

[Paper][Code]