{"type":"ScholarlyArticle","title":"DiverValue-Bench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values","authors":[{"name":"Yao Liang","slug":"yao-liang","given":"Yao","family":"Liang","affiliation":""},{"name":"Dongcheng Zhao","slug":"dongcheng-zhao","given":"Dongcheng","family":"Zhao","affiliation":""},{"name":"Feifei Zhao","slug":"feifei-zhao","given":"Feifei","family":"Zhao","affiliation":""},{"name":"Guobin Shen","slug":"guobin-shen","given":"Guobin","family":"Shen","affiliation":""},{"name":"Yuwei Wang","slug":"yuwei-wang","given":"Yuwei","family":"Wang","affiliation":""},{"name":"Dongqi Liang","slug":"dongqi-liang","given":"Dongqi","family":"Liang","affiliation":""},{"name":"Yi Zeng","slug":"yi-zeng","given":"Yi","family":"Zeng","affiliation":""}],"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.","doi":"10.24963/ijcai.2026/850","url":"https://ijcai.org/proceedings/2026/850","pdf":"https://ijcai.org/proceedings/2026/0850.pdf","markdown":"https://ijcai.org/proceedings/2026/850.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/850","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Human-Centred AI","track":"Human-Centred AI","number":850,"pages":{"first":7647,"last":7657},"keywords":["Human-Centred AI: Humans and AI","Human-Centred AI: Natural Language Processing","Human-Centred AI: AI Ethics, Trust, Fairnes"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}