​​

Foundation Models and LLMs

[Mechanism Design for LLMs, Uncertainty with AI Systems]

(Note:     students under my supervision;  † equal contribution;  * corresponding author)​​​​​

 

Mechanism Design for LLMs

​​​​

• Incentivizing truthful language models via peer elicitation games. [preprint][code]

Baiting Chen†, Tong Zhu†, Jiale Han, Lexin Li, Gang Li, and Xiaowu Dai*.

Advances in Neural Information Processing Systems (NeurIPS), 2025.​

​

• Competitive multi-agent delegation for LLM reasoning. [code​]

Tong Zhu†, Baiting Chen†, Jin Zhou, Hua Zhou, Sriram Sankararaman, and Xiaowu Dai*.

Preprint, 2025.

​

 

 

Uncertainty with AI Systems​​​

​

• Surrogate-powered inference: Regularization and adaptivity. 

Jianmin Chen, Huiyuan Wang, Thomas Lumley, Xiaowu Dai, and Yong Chen.

Under Major Revisions at Journal of the American Statistical Association (JASA), 2025

​

​

​

​

​

​