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
DiverValue-Bench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values
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。
摘要：
使大语言模型（LLMs）与多元人类价值观对齐对于安全有效的部署至关重要，但现有基准常忽视文化和人口统计学差异。我们推出DiverValue-Bench，这是一个面向人群的基准，用于评估覆盖74个国家/地区的多维价值观对齐。它包含23763个经质量控制的实例，这些实例源自PRISM用户反馈并通过大规模人工验证审核，具有细粒度价值观标签、个性化问题、对比参考答案及丰富人口统计元数据。利用DiverValue-Bench，我们评估了代表性LLMs，发现了被整体性能掩盖的显著地理和人口统计学差异。我们还表明，结合低秩适配（LoRA）与直接偏好优化（DPO）的轻量型基于偏好的微调，可显著提升领域内价值观对齐效果，同时在领域外也取得一致增益。这些结果凸显了面向人群的对齐评估的必要性，并证明DiverValue-Bench可作为全球对齐、个性化价值观建模及公平AI开发的实用基础。
英文摘要：
Aligning large language models (LLMs) with diverse human values is essential for safe and effective deployment, yet existing benchmarks often overlook cultural and demographic variation. We introduce DiverValue-Bench, a population-aware benchmark for evaluating multi-dimensional value alignment across 74 countries/regions. It contains 23,763 quality-controlled instances derived from PRISM user feedback and audited through large-scale human validation, with fine-grained value labels, personalized questions, contrastive reference answers, and rich demographic metadata. Using DiverValue-Bench, we evaluate representative LLMs and reveal substantial geographic and demographic disparities that are masked by aggregate performance. We further show that lightweight preference-based fine-tuning with Low-Rank Adaptation (LoRA) and Direct Preference Optimization (DPO) substantially improves in-domain value alignment while yielding consistent out-of-domain gains. These results highlight the need for population-aware alignment evaluation and demonstrate the utility of DiverValue-Bench as a practical foundation for global alignment, personalized value modeling, and equitable AI development.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
