1
Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models
研究大语言模型在角色扮演中的道德易感性与稳健性，揭示AI如何随人设改变道德判断。
arXiv:2511.08565v3 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly operate in social contexts, motivating analysis of…