Friday, March 1, 2024
10:20 a.m. – 11:10 a.m. (CST)
Dr. James Caverlee
Professor, Department of Computer Science and Engineering
Texas A&M University
ETB 1020
Title: “Thoughts on Large Language Models: Data Efficiency, Bias, and Long-Tails”
Abstract
In this talk, I will share some recent work from our lab and from Google DeepMind on several big challenges in Large Language Models including: 1) data efficiency: since pre-training LLMs is hugely expensive, can we develop data efficient methods to more intelligently select training examples? 2) bias: while advances in techniques to minimize explicit bias can superficially enable LLMs to avoid the perception of bias, can we indirectly probe LLMs to reveal their intrinsic bias? And develop methods towards mitigating this bias? 3) long-tails: LLMs can demonstrate strong performance on popular concepts, but in many cases there is a gap in the treatment of rare (or tail) concepts. Can we bridge this gap?
Biography
Dr. James Caverlee is a Professor in the Department of Computer Science and Engineering at Texas A&M University and a Visiting Researcher at Google DeepMind. His research focuses on connecting people to information, with an emphasis on algorithms and systems that are trustworthy, resilient, and responsible.
More on CESG Seminars: HERE
Please join on Friday, 03/01/24 at 10:20 a.m. in ETB 1020.