notesum.ai

Published at November 6

Evaluating Moral Beliefs across LLMs through a Pluralistic Framework

cs.CL

cs.AI

Released Date: November 6, 2024

Authors: Xuelin Liu¹, Yanfei Zhu¹, Shucheng Zhu², Pengyuan Liu³, Ying Liu², Dong Yu¹

Aff.: ¹School of Information Science, Beijing Language and Culture University, Beijing, China; ²School of Humanities, Tsinghua University, Beijing, China; ³School of Information Science, Beijing Language and Culture University, Beijing, China; National Print Media Language Resources Monitoring & Research Center, Beijing Language and Culture University, Beijing, China

Arxiv: http://arxiv.org/abs/2411.03665v1

	Social	Occupation	Family	Individual	Overall
ChatGLM	0.76	0.74	0.78	0.69	0.74
Ernie	0.72	0.67	0.75	0.61	0.69
Gemini	0.85	0.84	0.90	0.81	0.85
ChatGPT	0.94	0.94	0.94	0.91	0.93