Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning

ArXi:2506.20020v2 Announce Type: replace Reasoning in humans is prone to biases due to underlying motivations like identity protection, that undermine rational decision-making and judgment. This \textit{motivated reasoning} at a collective level can be detrimental to society when debating critical issues such as human-driven climate change or vaccine safety, and can further aggravate political polarization.