Interested Topics

• Misinformation
• Generative AI: Bias, Debiasing, and Watermarking
• LLM Foundations

Selected Publications

• Mao, M., Zhao, X., & Fang, X. (2026). Early Detection of Misinformation for Infodemic Management: A Domain Adaptation Approach. Accepted by Management Science. Paper

• Wei, D.*, Mao, M.*, Fang, X., & Chau, M. (2025). Short-PHD: Detecting Short LLM-generated Text with Topological Data Analysis After Off-topic Content Insertion. Corresponding author, COLM 2025. Paper Code.

• Mao, M.*, Wei, D.*, Chen, Z.*, Fang, X., & Chau, M. (2025). Watermarking Large Language Models: An Unbiased and Low-risk Method. Corresponding author, ACL 2025. Paper Code

• Fang, X., Che, S., Mao, M., Zhang, H., Zhao, M., & Zhao, X. (2024). Bias of AI-generated content: an examination of news produced by large language models. Scientific Reports, 14(1), 5224. Paper Data 2024 SCI top1% Cited Paper

• Wei, Y., Mao, M., Zhao, X., Zou, J., & An, P. (2020). City metro network expansion with reinforcement learning. ACM SIGKDD 2020. Paper Code

• Zhao, J.*, Mao, M.*, Zhao, X., & Zou, J. (2020). A hybrid of deep reinforcement learning and local search for the vehicle routing problems. IEEE Transactions on Intelligent Transportation Systems, 22(11), 7208-7218. Equal contributions. Paper

Articles Under Revision and Review

• Mao, M.*, Wei, D.*, Fang, X., & Chau, M. (2025). A General Model for Detecting Information Generated by Large Language Models. Under revision for third-round review at MIS Quarterly. Paper

• Mao, M., Yin, B., Chen, S., & Fang, X. Massive Activation Gating Channel in Large Language Models. Under review at International Conference on Learning Representations. Paper

• Mao, M.*, Yin, B.*, Zhu, Y., & Fang, X. (2025). Early Stopping Chain-of-thoughts in Large Language Models. Paper

Selected Working Paper

• Mao, M., & Yin, B. (2026). Tuning LLMs as Fact-Checkers: Reinforcement Learning for Evidence Tree Construction. Workshop on Information Technologies and Systems 2026.

• Yin, B., Mao, M., Chen, S., & Fang, X. Mitigating Stereotype Bias in LLM Decision Making. INFORMS data science workshop 2026.

• Yin, B., Zhu, Y., Mao, M., Zhang, H., & Fang, X.. Unleashing the Power of Large Language Models for Credit Risk Prediction: A Multi-view Time-Series LLM Approach. INFORMS data science workshop 2025.

• Chen, S., Mao, M., Zhao, M., & Fang, X. Debiasing Large Language Models: A Novel Approach to Mitigating Demographic Bias. INFORMS data science workshop 2025.

• Che, S.*, Mao, M.*, Zhang, H., Fang, X. & Liu, H. (2024). New Community Cold-Start Recommendation: A Novel Large Language Model-based Method. ICIS 2024 Best Student Paper Nominee. Paper