Postdoctoral Researcher, Allen Institute for AI and University of Washington
- Date & time
- Monday, October 23, 2023 · 1:00 PM
- Location
- Donald Bren Hall 4011
Abstract
Recently-released language models have attracted a lot of attention for their major successes and (often more subtle, but still plentiful) failures. In this talk, I will motivate why transparency into model operations is needed to rectify these failures and increase model utility in a reliable way. I will highlight how techniques must be developed in this changing NLP landscape for both open-source models and black-box models behind an API. I will provide an example of each from my recent work demonstrating how improved transparency can improve language model performance on downstream tasks.
About the speaker
Sarah Wiegreffe is a postdoc at the Allen Institute for AI (AI2), working on the Aristo project, and holds a courtesy appointment in the Allen School at the University of Washington. Her research focuses on language model transparency. She received her PhD from Georgia Tech in 2022.