Ze Wang
Hello! I am a PhD student in the Department of Economics at University College London, a PhD Scholar at the Stone Centre, a Research Affiliate at Holistic AI, and a Research Fellow at the Institute for the Future of Work. My research lies at the intersection of economics and artificial intelligence, focusing on how humans and AI systems co-adapt over time. I study the social impact, alignment, and interpretability of AI using tools from behavioral, cognitive, and experimental economics, as well as machine learning.
Publications
SAGED: A Holistic Bias-Benchmarking Pipeline for Language Models with Customisable Fairness Calibration. Proceedings of the 31st International Conference on Computational Linguistics.
JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models. Findings of the Association for Computational Linguistics: EMNLP 2024.
Work in progress
Large Language Models in Hiring.
Bias Amplification: Large Language Models as Increasingly Biased Media. Arxiv.
Bargaining game with reference-dependent preferences.
How does breastfeeding influence infant mortality? Insights from India.