CIIR Talk Series: Eunsol Choi

Speaker: Eunsol Choi, New York University

Talk Title: Rethinking Retrieval in the Era of LLM

Date: Friday, October 4, 2024 - 1:30 - 2:30 PM EDT (North American Eastern Daylight Saving Time)

Zoom Access: Zoom Link and reach out to Hamed Zamani or Dan Parker for the passcode.

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.