Hello,

Many of us use AI assistants like ChatCPT or Claude, but we may still struggle to understand how they work or why they get things wrong. A free seminar at CHI on Oct. 29 at 2:30 p.m. aims to close that knowledge gap, and I thought it might interest your grad students or other members in the College of Community and Global Health.

Foundations and Mechanisms of Modern Natural Language Processing and Large Language Models Presented by Dr. Lei Ding October 29, 2026 | 2:30 p.m. - 3:30 p.m. Chown Building, A474 The Classroom No registration required

Dr. Ding will explain how large language models generate text, from next-token prediction to instruction-following assistants. He will cover how the Transformer architecture uses context, and how pretraining and post-training shape a model's behaviour. He will then connect those ideas to everyday use: how prompts and retrieval-augmented generation affect a model's answers, and where errors can creep in.

The seminar is an accessible introduction. It is open to faculty, staff, trainees, students, and anyone interested in bioinformatics, biostatistics, or epidemiology. It's free, and no registration is required.

We would be grateful if you would share this with your department's students and members. Attached is a pdf poster appropriate for email or print.

Breana Kelly (she/her) Communications Specialist | Knowledge Mobilization ___________________________________________________ George & Fay Yee Centre for Healthcare Innovation E: bre.kelly@umanitoba.camailto:bre.kelly@umanitoba.ca P: (431) 275 4772 chimb.cahttps://chimb.ca/

Upcoming Absences No upcoming absences

[Signatures_Logo.jpg] Supported by the University of Manitoba, Shared Health, the Government of Manitoba and the Canadian Institutes for Health Research.