作者位次 #2/4ACL 2026Findings· Findings of ACL
Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning
Saloni Dash · Amélie Reymond · Emma Spiro · Aylin Caliskan
摘要
Reasoning in humans is prone to biases due to underlying motivations like identity protection, that undermine rational decision-making and judgment. This motivated reasoning at a collective level can be detrimental to society when debating critical issues such as human-driven climate change or va...