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

arXiv:2509.08022v3 Announce Type: replace-cross Abstract: 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.

Related

• Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective
• CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models
• Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
• Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
• Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning

Source: arXiv cs.AI | 2026-08-21