Speaker

Eric Wong, Assistant Professor, Department of Computer and Information Science, University of Pennsylvania

Abstract

Recent language models have introduced prompting: an easy-to-use language interface for instructing and fine-tuning both image and text generation models. However, these prompting interfaces can often have strange and unexpected behaviors. This has led to a substantial effort in manually designing and engineering better prompts. In this talk, I will discuss our recent works in integrating principles from optimization, influences, and program execution into prompting interfaces to turn "prompt engineering" into a reliable science.

Biography

Eric Wong is an Assistant Professor in the Department of Computer and Information Science at the University of Pennsylvania. His work focuses on the foundations of robust systems, building on elements of machine learning and optimization to debug, understand, and develop reliable systems. He is a 2020 Siebel Scholar and received an honorable mention for his thesis on the robustness of deep networks to adversarial examples at Carnegie Mellon University advised by Zico Kolter. Prior to joining UPenn, he was a postdoc at CSAIL MIT advised by Aleksander Madry.