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

​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.

​There are limited in-person spots, so please only RSVP if you intend to show up.

​If the $5 is a barrier to entry, please email us and we’ll be happy to offer you a free ticket.