CIIR Talk Series: Eunsol Choi, Rethinking Retrieval in the Era of LLM

Content

Image

Speaker 

Eunsol Choi, New York University

Abstract

In recent years, the progress in large-language models (LLMs) enabled the development of powerful dense retrieval systems. At the same time, retrieval systems became a crucial tool to complement LLMs by providing up-to-date or long-tail knowledge. In this talk, I will cover both sides of the story: how can we better interface LLM with retrieval systems and how LLMs enable studying the next generation of retrieval systems. I will first discuss our recent work in developing intermediate modules for scaling knowledge augmentation. Then, I will present our study in open-world evaluation of retrieving diverse perspectives for complex and contentious questions. I will conclude the talk with preliminary results in rethinking query representation for retrieval systems.

Bio

Eunsol Choi is an assistant professor of computer science and data science at New York University. Her research spans natural language processing and machine learning, with a focus on interpreting and reasoning about text in dynamic real-world contexts. Prior to joining NYU, she was an assistant professor at the University of Texas at Austin. She also spent a year at Google AI as a visiting researcher. She holds a Ph.D. in computer science and engineering from the University of Washington and a B.A. in mathematics and computer science from Cornell University. Outside of her academic pursuits, she enjoys nature and museums.

Subscribe to mailing list by sending an email to ciir-talks-request [at] cs [dot] umass [dot] edu (ciir-talks-request[at]cs[dot]umass[dot]edu) with "subscribe" as the email subject (without the quotation marks) for Zoom Link/Passcode notifications; or click here for Zoom link and reach out to zamani [at] cs [dot] umass [dot] edu (subject: CIIR%20Talks%20Passcode) (Hamed Zamani) or drp [at] cs [dot] umass [dot] edu (subject: CIIR%20Talks%20Passcode) (Dan Parker) for the passcode.