一作ACL 2026Poster· Natural Language Processing
How do Role Models Shape Collective Morality? Exemplar-Driven Moral Learning in Multi-Agent Simulation
Junjie Liao · Huacong Tang · Zhou Ziheng · Yizhou Wang · Fangwei Zhong
摘要
We investigate how role models shape collective morality. To explore this, we build a multi-agent simulation powered by a Large Language Models (LLMs), where agents with diverse intrinsic drives, ranging from cooperative to competitive, interact and adapt through a four-stage cognitive loop (plan...