Toronto and Michigan NLP Group for AI Safety

The Toronto and Michigan NLP Group for AI Safety links Zhijing Jin’s Jinesis AI Lab at the University of Toronto with collaborators at the University of Michigan to study how large language models behave in sensitive democratic and human-rights contexts. Their work includes analyzing when LLMs endorse limitations on principles in the Universal Declaration of Human Rights and developing evaluation protocols to better understand and constrain model behavior in such settings.

Endorsements support University of Toronto & University of Michigan.

No endorsements yet.

Discussion

Start Date

-

End Date

-

Expected Duration

-

Funding Raised to Date

-