Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2604.27553 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909003883216896 |
|---|---|
| author | Wang, Xiaomeng Larson, Martha Zhao, Zhengyu |
| author_facet | Wang, Xiaomeng Larson, Martha Zhao, Zhengyu |
| contents | When the visual style of text is considered, a wide variety can be observed in font, color, and size. However, when a word is read, its meaning is independent of the style in which it has been written or rendered. In this paper, we investigate whether, and how, the style in which a word is visualized in an image impacts the description that a Large Visual Language Model (LVLM) provides for the concept to which that word refers. Specifically, we investigate how functional text styles (readability-oriented, e.g., black sans-serif) versus decorative styles (display-oriented, e.g., colored cursive/script) affect LVLMs' descriptions of a concept in terms of the attributes of that concept. Our experiments study the situation in which the LVLM is able to correctly identify the concept referred to by a visual text, i.e., by a word or words rendered as an image, and in which the visual text style should not influence the attribute-based description that the LVLM produces. Our experimental results reveal that even when the concept is correctly identified, text style influences the model's attribute-based descriptions of the concept. Our findings demonstrate non-trivial style leakage from text style into semantic inference and motivate style-aware evaluation and mitigation for LVLM-based multimedia systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27553 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Revealing the Impact of Visual Text Style on Attribute-based Descriptions Produced by Large Visual Language Models Wang, Xiaomeng Larson, Martha Zhao, Zhengyu Computer Vision and Pattern Recognition When the visual style of text is considered, a wide variety can be observed in font, color, and size. However, when a word is read, its meaning is independent of the style in which it has been written or rendered. In this paper, we investigate whether, and how, the style in which a word is visualized in an image impacts the description that a Large Visual Language Model (LVLM) provides for the concept to which that word refers. Specifically, we investigate how functional text styles (readability-oriented, e.g., black sans-serif) versus decorative styles (display-oriented, e.g., colored cursive/script) affect LVLMs' descriptions of a concept in terms of the attributes of that concept. Our experiments study the situation in which the LVLM is able to correctly identify the concept referred to by a visual text, i.e., by a word or words rendered as an image, and in which the visual text style should not influence the attribute-based description that the LVLM produces. Our experimental results reveal that even when the concept is correctly identified, text style influences the model's attribute-based descriptions of the concept. Our findings demonstrate non-trivial style leakage from text style into semantic inference and motivate style-aware evaluation and mitigation for LVLM-based multimedia systems. |
| title | Revealing the Impact of Visual Text Style on Attribute-based Descriptions Produced by Large Visual Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.27553 |