JSSODa-test

# JSSODa (test)

[Paper](https://arxiv.org/abs/2511.15059) | [Code](https://github.com/llm-jp/eval_vertical_ja)

This repository contains the **test** split of the JSSODa dataset.

## Dataset details

JSSODa (**J**apanese **S**imple **S**ynthetic **O**CR **Da**taset) is constructed by rendering Japanese text generated by an LLM into images.
The images contain text written both vertically and horizontally, which is organized into one to four columns.

This dataset was introduced in our paper: ["Evaluating Multimodal Large Language Models on Vertically Written Japanese Text"](https://arxiv.org/abs/2511.15059).

The code used to generate this dataset is available at our GitHub repository: [https://github.com/llm-jp/eval_vertical_ja/tree/main/scripts](https://github.com/llm-jp/eval_vertical_ja/tree/main/scripts)

## License

This dataset is released under [Creative Commons Attribution 4.0 License](https://creativecommons.org/licenses/by/4.0/legalcode).

## Citation

```bibtex
@misc{sasagawa2025evaluatingmultimodallargelanguage,
title={Evaluating Multimodal Large Language Models on Vertically Written Japanese Text},
author={Keito Sasagawa and Shuhei Kurita and Daisuke Kawahara},
year={2025},
eprint={2511.15059},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2511.15059},
}
```

# JSSODa（测试集）
[论文](https://arxiv.org/abs/2511.15059) | [代码](https://github.com/llm-jp/eval_vertical_ja)

本仓库收录了JSSODa数据集的**测试子集**。

## 数据集详情

JSSODa（**J**apanese **S**imple **S**ynthetic **O**CR **Da**taset，日语简易合成OCR数据集）是通过将大语言模型（Large Language Model）生成的日语文本渲染为图像构建而成。生成的图像包含竖排与横排两种排版的文本，文本以1至4列的形式进行排布。

本数据集首次提出于我们的论文《面向竖排日语文本的多模态大语言模型评估》(https://arxiv.org/abs/2511.15059)。

本数据集的生成代码可于我们的GitHub仓库获取：[https://github.com/llm-jp/eval_vertical_ja/tree/main/scripts](https://github.com/llm-jp/eval_vertical_ja/tree/main/scripts)

## 许可协议

本数据集采用[知识共享署名4.0国际许可协议（Creative Commons Attribution 4.0 License）](https://creativecommons.org/licenses/by/4.0/legalcode)进行发布。

## 引用

bibtex
@misc{sasagawa2025evaluatingmultimodallargelanguage,
title={面向竖排日语文本的多模态大语言模型评估},
author={Keito Sasagawa and Shuhei Kurita and Daisuke Kawahara},
year={2025},
eprint={2511.15059},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2511.15059},
}

搜集汇总

背景与挑战

背景概述

JSSODa-test是JSSODa数据集的测试集，通过渲染日语文本生成图像，包含垂直和水平书写的文本，用于评估多模态大语言模型对垂直书写日语的处理能力。该数据集遵循CC BY 4.0许可协议。