Cover Image for AI Safety Thursdays: Can we make LLMs forget? An Intro to Machine Unlearning

Presented by

Catalyzing Toronto's role in steering AI progress toward a future of human flourishing. Join us for a variety of events on technical AI safety, governance in a world of advanced AI, and more.

Hosted By

1 Going

AI

AI Safety Thursdays: Can we make LLMs forget? An Intro to Machine Unlearning

Name: AI Safety Thursdays: Can we make LLMs forget? An Intro to Machine Unlearning
Start: 2025-08-21T18:00:00.000-04:00
End: 2025-08-21T21:00:00.000-04:00
Location: 30 Adelaide St E 12th floor

Trajectory Labs

30 Adelaide St E 12th floor

Toronto, Ontario

Welcome! Please choose your desired ticket type:

You will be asked to verify token ownership with your wallet.

About Event

LLMs are pre-trained on a large fraction of the internet. As a result, they can regurgitate private, copyrighted, and potentially hazardous information, causing deployment and safety challenges.

Lev McKinney will guide us through machine unlearning in LLMs—how models retain facts, methods for identifying influential training data, and techniques for suppressing predictions. Finally, we'll assess current research and its effectiveness for policy and safety concerns.

Timeline

6:00 to 6:30 - Food & Networking

6:30 to 7:30 - Main Presentation & Questions

7:30 to 8:00 - Discussion

If you can't make it in person, feel free to join the live stream at 6:30 pm, via this link.

Location