Self-promo
Trustworthy AI workshop to explore hallucinations and reliable autonomy
The Simons Institute invited attendees; its workshop listing describes an exploratory look at explaining and mitigating AI hallucinations.
TLDR
The Simons Institute shared an invitation to its “Trustworthy AI: From Hallucinations to Reliable Autonomy” workshop. The Berkeley listing says it will consider ways to explain and mitigate hallucinations in generative models, across settings including text, graph-structured data and continuous data. It also welcomes work on trade-offs with generalization and creativity.
Combined views
17
1 Source, first seen ago