MVPBench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909789643079680 |
|---|---|
| author | Liang, Yao Zhao, Dongcheng Zhao, Feifei Shen, Guobin Wang, Yuwei Liang, Dongqi Zeng, Yi |
| author_facet | Liang, Yao Zhao, Dongcheng Zhao, Feifei Shen, Guobin Wang, Yuwei Liang, Dongqi Zeng, Yi |
| contents | The alignment of large language models (LLMs) with human values is critical for their safe and effective deployment across diverse user populations. However, existing benchmarks often neglect cultural and demographic diversity, leading to limited understanding of how value alignment generalizes globally. In this work, we introduce MVPBench, a novel benchmark that systematically evaluates LLMs' alignment with multi-dimensional human value preferences across 75 countries. MVPBench contains 24,020 high-quality instances annotated with fine-grained value labels, personalized questions, and rich demographic metadata, making it the most comprehensive resource of its kind to date. Using MVPBench, we conduct an in-depth analysis of several state-of-the-art LLMs, revealing substantial disparities in alignment performance across geographic and demographic lines. We further demonstrate that lightweight fine-tuning methods, such as Low-Rank Adaptation (LoRA) and Direct Preference Optimization (DPO), can significantly enhance value alignment in both in-domain and out-of-domain settings. Our findings underscore the necessity for population-aware alignment evaluation and provide actionable insights for building culturally adaptive and value-sensitive LLMs. MVPBench serves as a practical foundation for future research on global alignment, personalized value modeling, and equitable AI development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_08022 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MVPBench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values Liang, Yao Zhao, Dongcheng Zhao, Feifei Shen, Guobin Wang, Yuwei Liang, Dongqi Zeng, Yi Computation and Language Artificial Intelligence The alignment of large language models (LLMs) with human values is critical for their safe and effective deployment across diverse user populations. However, existing benchmarks often neglect cultural and demographic diversity, leading to limited understanding of how value alignment generalizes globally. In this work, we introduce MVPBench, a novel benchmark that systematically evaluates LLMs' alignment with multi-dimensional human value preferences across 75 countries. MVPBench contains 24,020 high-quality instances annotated with fine-grained value labels, personalized questions, and rich demographic metadata, making it the most comprehensive resource of its kind to date. Using MVPBench, we conduct an in-depth analysis of several state-of-the-art LLMs, revealing substantial disparities in alignment performance across geographic and demographic lines. We further demonstrate that lightweight fine-tuning methods, such as Low-Rank Adaptation (LoRA) and Direct Preference Optimization (DPO), can significantly enhance value alignment in both in-domain and out-of-domain settings. Our findings underscore the necessity for population-aware alignment evaluation and provide actionable insights for building culturally adaptive and value-sensitive LLMs. MVPBench serves as a practical foundation for future research on global alignment, personalized value modeling, and equitable AI development. |
| title | MVPBench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.08022 |