多模态视觉语言模型的区域人文适配：GG-EZ 方法在东南亚实现 5-15% 文化相关性提升
Anthropogenic Regional Adaptation in Multimodal Vision-Language Model
研究者提出“区域人文适配”新范式及 GG-EZ 适配方法，通过区域数据过滤与模型合并，让视觉语言模型贴合特定地区语境。在大型视觉语言模型、文生图扩散模型和视觉语言嵌入模型 3 类架构上实验，东南亚案例显示文化相关性指标提升 5-15%，同时保留超 98% 的全球性能。
Authors:Samuel Cahyawijaya, Peerat Limkonchotiwat, Tack Hwa Wong, Hitesh Laxmichand Patel, Amit Agarwal, Manuel Antonio Rufino, Carlos Rafael Catalan, Muhammad Reza Qorib, Vicky Feliren, Holy Lovenia, Aye Hninn Khine, Frederikus Hudi, David Anugraha, Alham Fikri Aji, Romrawin Chumpu, Viet-Thanh Pham, Minghan Wang, Mohamed Fazli Imam, Ruochen Zhang, Joseph Marvin Imperial, Khumaisa Nur'aini, Do Xuan Long, Musa Izzanardi Wijanarko, Joel Ruben Antony Moniz, Patrick Amadeus Irawan, Hanif Muhammad Zhafran, Isaiah Flores, Salsabila Zahirah Pranida, Jun Kevin, Jostin Jerico Rosal, Patricia Nicole Monderin, Kun Kerdthaisong, Ahmad Mustafid, My Chiffon Nguyen, Natchapon Jongwiriyanurak, Siva Worajitwannakul, Haochen Li, Adrian Xuan Wei Lim, Bin Wang, Muhammad Ravi Shulthan Habibi, Lynnette Hui Xian Ng, Mithil Bangera, Yeshil Bangera, Priyaranjan Pattnayak, Dun Li Chan, Sherissa Caren Djuniwar, Cho Chan Myei Oo, Hee Ming Shan
Abstract:While the field of vision-language (VL) has achieved remarkable success in integrating visual and textual information across multiple languages and domains, there is still no dedicated framework for assessing human-centric alignment in vision-language systems. We offer two contributions to address this gap. First, we introduce Anthropogenic Regional Adaptation: a novel paradigm that aims to optimize model relevance to specific regional contexts while ensuring the retention of global generalization capabilities. Second, we present a simple, but effective adaptation method named Geographical-generalization-made-easy (GG-EZ), which utilizes regional data filtering and model merging. Through comprehensive experiments on 3 VL architectures: large vision-language models, text-to-image diffusion models, and vision-language embedding models, and a case study in Southeast Asia (SEA) regional adaptation, we demonstrate the importance of Anthropogenic Regional Adaptation and the effectiveness of GG-EZ, showing 5-15% gains in cultural relevance metrics across SEA while maintaining over 98% of global performance and even occasionally surpassing it. Our findings establish Anthropogenic Regional Alignment as a foundational paradigm towards applicability of multimodal vision-language models in diverse regions and demonstrate a simple-yet-effective baseline method that optimizes regional value alignment while preserving global generalization.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2604.11490 [cs.AI] |
| (or arXiv:2604.11490v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2604.11490 arXiv-issued DOI via DataCite |
Submission history
From: Tack Hwa Wong [view email]
[v1]
Mon, 13 Apr 2026 13:56:00 UTC (7,028 KB)
[v2]
Thu, 16 Apr 2026 23:50:04 UTC (7,028 KB)
[v3]
Sat, 31 Oct 2026 05:25:53 UTC (7,045 KB)
来源：arXiv cs.CL · arxiv.org