Bio: Zhenyu "James" Kong is the Ralph H. Bogle Jr. Professor in the Grado Department of Industrial and Systems Engineering at Virginia Tech. He received his BS and MS in Mechanical Engineering from the Harbin Institute of Technology and his PhD in Industrial and Systems Engineering from the University of Wisconsin-Madison in 2004. His research focuses on sensing and analytics for smart manufacturing, modeling and diagnosis of large and complex manufacturing systems, and machine learning for manufacturing applications, and he is a Fellow of the Institute of Industrial and Systems Engineers.This talk consists of two parts. In the first part, we study the inference reliability of large language models (LLMs), with an emphasis on characterizing how prompt design affects the accuracy and stability of model outputs. We discuss recent theoretical and empirical advances in in-context learning and hallucination, and examine conditions under which LLMs produce reliable predictions. In the second part, we consider constrained bilevel optimization and develop efficient algorithms with provable guarantees. In particular, we show how error bound conditions can be leveraged to obtain fast convergence rates under mild assumptions.