When:
Wednesday, May 1, 2024
12:00 PM - 1:00 PM CT
Where: Mudd Hall ( formerly Seeley G. Mudd Library), 3514, 2233 Tech Drive, Evanston, IL 60208 map it
Audience: Faculty/Staff - Student - Post Docs/Docs - Graduate Students
Cost: free
Contact:
Wynante R Charles
(847) 467-8174
Group: Department of Computer Science (CS)
Category: Academic
Wednesday / CS Distinguished Lecture
May 1st / 12:00 PM
Hybrid / Mudd 3514
Speaker
Tong Zhang, University of Illinois Urbana-Champaign
Talk Title
Machine Learning Methods for Finetuning and Alignment of Large Language Models
Abstract
Large Language Models (LLMs) represent a significant milestone in the development of artificial general intelligence. Numerous pretrained models are available within the open-source community, yet they often require further training to be effectively utilized in downstream applications. The enhancement of these models is primarily accomplished through two methods: finetuning and Reinforcement Learning from Human Feedback (RLHF). Finetuning is crucial for tailoring LLMs to specialized topics or for developing capabilities such as instruction following. Meanwhile, RLHF aims to align LLMs with human preferences.
This talk presents various machine learning problems and algorithms for both finetuning and RLHF. For finetuning, we will introduce techniques that minimize hallucinations and enhance resource efficiency in optimization processes. For RLHF, we will explore both the theoretical frameworks that establish principled approaches and the practical algorithms that implement these theories. The presentation highlights some key questions and solutions in optimizing LLMs for enhanced functionality and alignment with human preferences.
Biography
Tong Zhang is currently a professor in the Computer Science department at the University of Illinois Urbana Champaign. He is a fellow of the IEEE, American Statistical Association, and Institute of Mathematical Statistics. His research interests include machine learning theory, algorithms, and applications. Tong Zhang has served as the chair or area chair in major machine learning conferences such as NeurIPS, ICML, and COLT, and has also served on the editorial boards of leading machine learning journals such as PAMI, JMLR, and the Machine Learning Journal.
Research Area/Interests
Data Mining; Machine Learning; Natural Language Processing
Zoom: https://northwestern.zoom.us/j/99555833103?pwd=TEtaakVGL2xUYytDa2Nvbk14Z3VhUT09