发表机构
NASK National Research Institute（NASK国家研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有英语中心视觉-语言模型在文化理解上的不足，推出波兰语单文化视觉-语言基准 PoVisLE，含1117张图像与2366对标注VQA样本，可评估深层文化多模态理解。
AI 中文摘要
视觉-语言模型（VLMs）在图像描述、视觉问答（VQA）、图像到文本生成等任务上已取得出色性能，但它们大多基于以英语为中心的数据进行训练，这限制了其处理基于文化的视觉理解的能力，导致在解读特定区域含义、符号内容及依赖上下文的视觉线索时出现错误。现有的文化能力基准通常是模板驱动的，且聚焦于表面级识别，不足以评估文化场景下更深层次的语言和语用理解。我们推出 PoVisLE，这是一个专为波兰语设计的单文化视觉-语言基准，用于在基于视觉上下文交互解释语言的 grounded 评估范式下，评估基于文化的多模态理解。该数据集包含 1117 张图像和 2366 对人工标注的 VQA 样本。总体而言，我们的数据集提供了一种可控且具有挑战性的资源，用于评估超越表面级识别的、基于文化的视觉-语言理解。
英文摘要
Vision-language models (VLMs) have achieved strong performance on tasks such as image captioning, visual question answering, and image-to-text generation. However, they are predominantly trained on English-centric data, which limits their ability to handle culturally grounded visual understanding and leads to failures in interpreting region-specific meanings, symbolic content, and context-dependent visual cues. Existing benchmarks for cultural competence are often template-driven and focused on surface-level recognition, making them insufficient for evaluating deeper linguistic and pragmatic understanding in culturally situated settings. We introduce PoVisLE, a monocultural vision-language benchmark for Polish designed to evaluate culturally grounded multimodal understanding under a grounded evaluation paradigm, where language is interpreted in interaction with visual context. The dataset contains 1,117 images and 2,366 manually annotated VQA pairs. Overall, our dataset provides a controlled and challenging resource for assessing culturally grounded vision-language understanding beyond surface-level recognition.
Comments28 pages. Preprint under review
