Join us for an exciting seminar led by Qinyuan Ye, PhD Student in Computer Science and James Flemings, PhD Student in Computer Science. To register, visit: https://usc.zoom.us/meeting/register/tJYvfuyrqD4oE9EEcrTwX0OHNFAWnq7Eou3-

Speaker: Qinyuan Ye

Talk: Cross-Task Generalization Abilities of Large Language Models

Humans can learn a new language task efficiently with only few examples, by leveraging their knowledge and experience obtained when learning prior tasks. Enabling similar cross-task generalization abilities in NLP systems is fundamental for approaching the goal of general intelligence and expanding the reach of language technology in the future. In this talk, I will present my work on (1) benchmarking cross-task generalization abilities with diverse NLP tasks; (2) developing model architectures for improving cross-task generalization abilities; (3) analyzing and predicting the generalization landscape of current state-of-the-art large language models.

Speaker: James Flemings

Talk: Privacy in the Era of Large Language Models

In this talk, I will motivate why privacy is needed for large language models, then I will discuss the challenges of providing privacy, the existing solutions, and future directions.