About
I am a third-year PhD student at King's College London, supervised by Prof. Jie M. Zhang, and a visiting student at the Southern University of Science and Technology, supervised by Prof. Yepang Liu. Previously, I earned my MSc from the University of Birmingham with Prof. Edward Tarte and my BEng from Guangzhou University with Prof. Zhijia Zhao. I am committed to advancing trustworthy and reliable AI software and agents. My research interests primarily focus on AI agents, AI ethics, AI4Healthcare, SE4AI.
News
Paper accepted at FSE 2026 — “Fairness Testing of Large Language Models in Role-Playing”
Paper accepted at ICSE 2026 — “Fairness Is Not Just Ethical: Performance Trade-Off via Data Correlation Tuning to Mitigate Bias in ML Software”
Paper accepted in Philosophical Transactions of the Royal Society A — “Mitigating Medical Bias in Large Language Models by Prompt Engineering”
Paper accepted at FSE 2024 — “MirrorFair: Fixing Fairness Bugs in Machine Learning Software via Counterfactual Predictions”
Selected Publications
Fairness Testing of Large Language Models in Role-Playing
Proceedings of the ACM on Software Engineering (FSE 2026), 2026
Fairness Is Not Just Ethical: Performance Trade-Off via Data Correlation Tuning to Mitigate Bias in ML Software
IEEE/ACM 48th International Conference on Software Engineering, 2026
Mitigating Medical Bias in Large Language Models by Prompt Engineering: An Empirical Study of Effectiveness and Trade-offs
Philosophical Transactions of the Royal Society A
Software Fairness Dilemma: Is Bias Mitigation a Zero-Sum Game?
Proceedings of the ACM on Software Engineering (FSE 2025)
MirrorFair: Fixing Fairness Bugs in Machine Learning Software via Counterfactual Predictions
Proceedings of the ACM on Software Engineering (FSE 2024)
A Comprehensive Study of Real-World Bugs in Machine Learning Model Optimization
IEEE/ACM 45th International Conference on Software Engineering, 2023
Preprints
Bias in Large AI Models for Medicine and Healthcare: Survey and Challenges
AMQA: An Adversarial Dataset for Benchmarking Bias of LLMs in Medicine and Healthcare
FITNESS: A Causal De-correlation Approach for Mitigating Bias in Machine Learning Software
Invited Talks
Mitigating machine learning software bias via correlation tuning — London, United Kingdom
Mitigating machine learning software bias via ensembling counterfactual predictions — Porto de Galinhas, Brazil