IJCAI

DiverValue-Bench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values

DiverValue-Bench：用于使大语言模型与多元人类价值观对齐的基准及微调框架

Yao Liang, Dongcheng Zhao, Feifei Zhao, Guobin Shen, Yuwei Wang, Dongqi Liang, Yi Zeng

AI总结 该研究推出覆盖74个国家/地区的人群感知基准DiverValue-Bench，发现现有LLMs存在地理与人口统计学价值观对齐差异，结合LoRA与DPO的轻量微调可提升对齐效果，为全球公平AI开发提供实用基础。

Comments 11 pages, 5 figures. Accepted to IJCAI-ECAI 2026 (Human-Centred AI Special Track). v2: Updated to the camera-ready version