Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.01419 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909937762828288 |
|---|---|
| author | Pranav, Tushar Pandey, Eshan Bala, Austria Lyka Diane Chadha, Aman Atmosukarto, Indriyati Lock, Donny Soh Cheng |
| author_facet | Pranav, Tushar Pandey, Eshan Bala, Austria Lyka Diane Chadha, Aman Atmosukarto, Indriyati Lock, Donny Soh Cheng |
| contents | Vision-Language Models (VLMs) excel in multimodal tasks but often exhibit Western-centric biases, limiting their effectiveness in culturally diverse regions like Southeast Asia (SEA). To address this, we introduce RICE-VL, a novel benchmark evaluating VLM cultural understanding across 11 ASEAN countries. RICE-VL includes over 28,000 human-curated Visual Question Answering (VQA) samples -- covering True or False, Fill-in-the-Blank, and open-ended formats -- and 1,000 image-bounding box pairs for Visual Grounding, annotated by culturally informed experts across 14 sub-ground categories. We propose SEA-LAVE, an extension of the LAVE metric, assessing textual accuracy, cultural alignment, and country identification. Evaluations of six open- and closed-source VLMs reveal significant performance gaps in low-resource countries and abstract cultural domains. The Visual Grounding task tests models' ability to localize culturally significant elements in complex scenes, probing spatial and contextual accuracy. RICE-VL exposes limitations in VLMs' cultural comprehension and highlights the need for inclusive model development to better serve diverse global populations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_01419 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rice-VL: Evaluating Vision-Language Models for Cultural Understanding Across ASEAN Countries Pranav, Tushar Pandey, Eshan Bala, Austria Lyka Diane Chadha, Aman Atmosukarto, Indriyati Lock, Donny Soh Cheng Computer Vision and Pattern Recognition Artificial Intelligence Vision-Language Models (VLMs) excel in multimodal tasks but often exhibit Western-centric biases, limiting their effectiveness in culturally diverse regions like Southeast Asia (SEA). To address this, we introduce RICE-VL, a novel benchmark evaluating VLM cultural understanding across 11 ASEAN countries. RICE-VL includes over 28,000 human-curated Visual Question Answering (VQA) samples -- covering True or False, Fill-in-the-Blank, and open-ended formats -- and 1,000 image-bounding box pairs for Visual Grounding, annotated by culturally informed experts across 14 sub-ground categories. We propose SEA-LAVE, an extension of the LAVE metric, assessing textual accuracy, cultural alignment, and country identification. Evaluations of six open- and closed-source VLMs reveal significant performance gaps in low-resource countries and abstract cultural domains. The Visual Grounding task tests models' ability to localize culturally significant elements in complex scenes, probing spatial and contextual accuracy. RICE-VL exposes limitations in VLMs' cultural comprehension and highlights the need for inclusive model development to better serve diverse global populations. |
| title | Rice-VL: Evaluating Vision-Language Models for Cultural Understanding Across ASEAN Countries |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.01419 |