Cross-institutional AI safety collaboration between the Jinesis AI Lab at the University of Toronto & Vector Institute and researchers at the University of Michigan, focused on auditing how large language models handle human-rights and other high-stakes social questions.
Endorsements support University of Toronto & University of Michigan.
Cross-institutional AI safety collaboration between the Jinesis AI Lab at the University of Toronto & Vector Institute and researchers at the University of Michigan, focused on auditing how large language models handle human-rights and other high-stakes social questions.
Endorsements support University of Toronto & University of Michigan.
People– no linked people
Updated 05/18/26 · By grantmaking.aiProject Details
Updated 05/18/26 · By grantmaking.aiThe 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.
Grants Received
Updated 05/18/26 · By grantmaking.aiDiscussion
No comments yet. Be the first to share your thoughts.