About

The success of generative models to scale has come with hallucinations. They force the community to think: "When are model generations accurate and truthful?" In this workshop, we will consider novel perspectives and formulations that can explain and mitigate hallucinations in generative models, making them more robust and leading  to overall accurate synthesis. During the workshop, we will focus both on discrete settings, e.g., text or graph-structured data, as well as continuous settings across a broad family of models. The workshop is intended to be exploratory; we welcome novel theoretical understanding and trade-offs with generalization and creativity.


 

Chairs/Organizers
Sharon Li
Sharon Li
(University of Wisconsin-Madison)
Register

Registration is required for in-person attendance, access to the livestream, and early access to the recording. Space may be limited, and you are advised to register early. 

For additional information please visit: https://simons.berkeley.edu/participating-workshop.

Please note: the Simons Institute regularly captures photos and video of activity around the Institute for use in videos, publications, and promotional materials. 

Register Now