Many LLMs Are More Utilitarian Than One

Dr. Anita Keshmirian, our Assistant Professor in Psychology and Data Science, together with co-author Razan Baltaji, explored how large language models reason collectively in moral dilemmas. Their paper, “Many LLMs Are More Utilitarian Than One”, has been accepted at NeurIPS 2025.

Link: Many LLMs Are More Utilitarian Than One