- This event has passed.
ASSET Seminar: Using Large Language Models to Build Explainable Classifiers, Chris Callison-Burch (University of Pennsylvania)
February 8 at 12:00 PM - 1:30 PM
I’ll present research on using large language models (LLMs) to build explainable classifiers. I will show off work from my PhD students and collaborators on several recent research directions:
- Image classification with explainable features (https://arxiv.org/abs/2211.
- Text classification with explainable features (work in progress)
- The importance of faithfulness in explanations (https://arxiv.org/abs/2209.
- (Time permitting) A faithful “chain of thought” LLM reasoner that produces code in its explanations (https://arxiv.org/abs/2301.
Here’s an example of the automatically generated concepts that we use for image classification in the first
The papers that I’ll present are joint work with:
Adam Stein, Ajay Patel, Ansh Kothary, Artemis Panagopoulou, Daniel Jin, Delip Rao, Eric Wong, Harry Li Zhang, Kathleen McKeown, Marianna Apidianaki, Mark Yatskar, Shenghao Zhou, Shreya Havaldar, Veronica Qing Lyu, Yue Yang, and othe
Associate Professor of Computer and Information Science, University of Pennsylvania
Chris Callison-Burch is an associate professor of Computer and Information Science at the University of Pennsylvania. His course on Artificial Intelligence has one of the highest enrollments at the university with 500 students taking the class each Fall.
He is best known for his research into statistical machine translation, paraphrasing and crowdsourcing. His current research is focused on applications of large language models to long-standing challenge problems in artificial intelligence. His PhD students joke that now whenever they ask him anything his first response is “Have you tried GPT-3 for that?”
Prof Callison-Burch has more than 100 publications, which have been cited over 20,000 times. He is a Sloan Research Fellow, and he has received faculty research awards from Google, Microsoft, Amazon, Facebook, and Roblox, in addition to funding from DARPA, IARPA, and the NSF.