ChinaHeritaQA：面向中国世界遗产地的文化基础视觉问答数据集
ChinaHeritaQA: A Culturally-Grounded Visual Question Answering Dataset for World Heritage Sites in China
AI总结：
提出ChinaHeritaQA多模态基准数据集，包含2279张图像和14133个双语多项选择题，覆盖七个认知维度，评估视觉语言模型在中国世界遗产上的文化推理能力。
摘要：
我们介绍了ChinaHeritaQA，这是一个多模态基准数据集，用于评估视觉语言模型（VLM）在中国联合国教科文组织世界遗产地上的文化推理能力。该数据集包含2279张野外图像，配以14133个双语（中文/英文）多项选择题对，涵盖七个认知维度，从基本身份识别到历史分期和建筑分析。在联合国教科文组织对齐的本体论指导下，并通过严格的人工注释验证，该数据集确保了语言质量和事实一致性。对最先进VLM的评估显示，虽然顶级模型在平均表现上超过人类，但出现了显著的任务级差异：模型在视觉识别方面表现出色，但在文化基础推理上存在困难。性能也因朝代和地区而异。ChinaHeritaQA揭示了强大的视觉检索能力并不能延伸到文化和历史理解。我们发布该数据集以支持未来关于文化感知多模态学习的研究。
英文摘要：
We introduce ChinaHeritaQA, a multimodal benchmark dataset for evaluating the cultural reasoning abilities of vision-language models (VLMs) on UNESCO World Heritage sites in China. The dataset comprises 2,279 in-the-wild images paired with 14,133 bilingual (Chinese/English) multiple-choice QA pairs spanning seven cognitive dimensions, from basic identity recognition to historical periodization and architectural analysis. Guided by a UNESCO-aligned heritage ontology and verified through rigorous human annotation, the dataset ensures linguistic quality and factual consistency. Evaluations of state-of-the-art VLMs reveal that while top models exceed human performance on average, substantial task-level variation emerges: models excel at visual recognition but struggle with culturally grounded reasoning. Performance also varies by dynasty and region. ChinaHeritaQA reveals that strong visual retrieval does not extend to cultural and historical understanding. We release the dataset to support future research on culturally aware multimodal learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
