arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2507.00700cs.CL

视觉-语言模型中的认知风格对比:日语中的整体性注意与英语中的分析性聚焦

Contrasting Cognitive Styles in Vision-Language Models: Holistic Attention in Japanese Versus Analytical Focus in English

University of Tartu(塔尔图大学);University of Ljubljana(卢布尔雅那大学);Sansan, Inc.(Sansan公司);Plaksha University(Plaksha大学)

Ahmed Sabir, Azinovič Gasper, Mengsay Loem, Rajesh Sharma

AI总结:

本文通过比较日语和英语训练的视觉-语言模型在图像描述中的注意模式,发现模型不仅内化语言结构,还会复现训练数据中的文化认知倾向,表明文化因素会隐含影响模型输出。

摘要:

关于感知与认知的跨文化研究表明,来自不同文化背景的个体以不同方式处理视觉信息。例如,东亚人倾向于采取整体性视角,关注情境关系,而西方人通常采用分析性方法,聚焦于个别对象及其属性。在本研究中,我们考察了主要在不同语言(特别是日语和英语)上训练的视觉-语言模型(VLMs)是否表现出类似的基于文化的注意模式。通过对图像描述的比较分析,我们检验这些模型是否反映了整体性与分析性倾向之间的差异。我们的研究结果表明,视觉-语言模型不仅内化了语言的结构属性,还再现了嵌入在训练数据中的文化行为,这表明文化认知可能以隐含方式塑造模型输出。

英文摘要:

Cross-cultural research in perception and cognition has shown that individuals from different cultural backgrounds process visual information in distinct ways. East Asians, for example, tend to adopt a holistic perspective, attending to contextual relationships, whereas Westerners often employ an analytical approach, focusing on individual objects and their attributes. In this study, we investigate whether Vision-Language Models (VLMs) trained predominantly on different languages, specifically Japanese and English, exhibit similar culturally grounded attentional patterns. Using comparative analysis of image descriptions, we examine whether these models reflect differences in holistic versus analytic tendencies. Our findings suggest that VLMs not only internalize the structural properties of language but also reproduce cultural behaviors embedded in the training data, indicating that cultural cognition may implicitly shape model outputs.

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。

↑