khhuang/CHOCOLATE
收藏资源简介:
--- annotations_creators: - expert-generated - found language_creators: - expert-generated - found language: - en license: apache-2.0 multilinguality: - monolingual size_categories: - 1K<n<10K paperswithcode_id: chocolate pretty_name: CHOCOLATE tags: - chart - plot - chart-to-text - vistext - statista - pew - chart-understanding - chart-captioning - chart-summarization - document-image configs: - config_name: default data_files: - split: test path: chocolate.json --- # Dataset Card for CHOCOLATE - [Dataset Description](https://huggingface.co/datasets/khhuang/CHOCOLATE/blob/main/README.md#dataset-description) - [Paper Information](https://huggingface.co/datasets/khhuang/CHOCOLATE/blob/main/README.md#paper-information) - [Citation](https://huggingface.co/datasets/khhuang/CHOCOLATE/blob/main/README.md#citation) ## Dataset Description **CHOCOLATE** is a benchmark for detecting and correcting factual inconsistency in generated chart captions. It consists of captions produced by six most advanced models, which are categorized into three subsets: - **LVLM**: GPT-4V, Bard (before Gemini) - **LLM-based Pipeline**: DePlot + GPT-4 - **Fine-tuned Model**: ChartT5, MatCha, UniChart The charts are from two datasets: VisText and the Pew split of Chart-to-Text. In total, **CHOCOLATE** consists of **1,187 examples**. Each instance in **CHOCOLATE** consists of a caption generated by one of the model and the annotations of the factual errors for each caption sentence. ## Paper Information - Paper: https://arxiv.org/abs/2312.10160 - Code: https://github.com/khuangaf/CHOCOLATE/ - Project: https://khuangaf.github.io/CHOCOLATE ## Citation If you use the **CHOCOLATE** dataset in your work, please kindly cite the paper using this BibTeX: ``` @misc{huang-etal-2023-do, title = "Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning", author = "Huang, Kung-Hsiang and Zhou, Mingyang and Chan, Hou Pong and Fung, Yi R. and Wang, Zhenhailong and Zhang, Lingyu and Chang, Shih-Fu and Ji, Heng", year={2023}, eprint={2312.10160}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
annotations_creators: - 专家生成 - 公开获取 language_creators: - 专家生成 - 公开获取 language: - 英语(en) license: Apache-2.0许可证 multilinguality: - 单语言 size_categories: - 1000 < 样本数 < 10000 paperswithcode_id: chocolate pretty_name: CHOCOLATE tags: - 图表(chart) - 绘图(plot) - 图表转文本(chart-to-text) - 视觉文本(VisText) - Statista - 皮尤(Pew) - 图表理解(chart-understanding) - 图表标题生成(chart-captioning) - 图表摘要(chart-summarization) - 文档图像(document-image) configs: - 配置名称:默认配置(default) 数据文件: - 拆分方式:测试集(test) 文件路径:chocolate.json --- # CHOCOLATE 数据集卡片 - [数据集说明](https://huggingface.co/datasets/khhuang/CHOCOLATE/blob/main/README.md#dataset-description) - [论文信息](https://huggingface.co/datasets/khhuang/CHOCOLATE/blob/main/README.md#paper-information) - [引用方式](https://huggingface.co/datasets/khhuang/CHOCOLATE/blob/main/README.md#citation) ## 数据集说明 **CHOCOLATE** 是一款用于检测并修正生成式图表标题中事实不一致性的评测基准数据集。该数据集包含由当前六款最先进模型生成的图表标题,这些模型被划分为三个子集: - **大视觉语言模型(LVLM)**:GPT-4V、Gemini发布前的Bard - **基于大语言模型的流水线模型**:DePlot + GPT-4 - **微调模型**:ChartT5、MatCha、UniChart 所用图表来源于两个数据集:视觉文本(VisText)数据集以及图表转文本(Chart-to-Text)数据集的皮尤(Pew)拆分子集。**CHOCOLATE** 总计包含**1187个样本**。数据集中的每个样本均包含由上述某一模型生成的标题,以及针对标题每一句的事实错误标注。 ## 论文信息 - 论文:https://arxiv.org/abs/2312.10160 - 代码:https://github.com/khuangaf/CHOCOLATE/ - 项目页面:https://khuangaf.github.io/CHOCOLATE ## 引用说明 若您在研究工作中使用 **CHOCOLATE** 数据集,请采用以下BibTeX格式引用该论文: @misc{huang-etal-2023-do, title = "Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning", author = "Huang, Kung-Hsiang and Zhou, Mingyang and Chan, Hou Pong and Fung, Yi R. and Wang, Zhenhailong and Zhang, Lingyu and Chang, Shih-Fu and Ji, Heng", year={2023}, eprint={2312.10160}, archivePrefix={arXiv}, primaryClass={cs.CL} }
数据集卡片 CHOCOLATE
数据集描述
CHOCOLATE 是一个用于检测和纠正生成图表标题中事实不一致性的基准数据集。它包含由六个最先进的模型生成的标题,分为三个子集:
- LVLM: GPT-4V, Bard (before Gemini)
- LLM-based Pipeline: DePlot + GPT-4
- Fine-tuned Model: ChartT5, MatCha, UniChart
图表来自两个数据集:VisText 和 Chart-to-Text 的 Pew 分割。CHOCOLATE 总共包含 1,187 个示例。CHOCOLATE 中的每个实例包含由其中一个模型生成的标题以及每个标题句子的事实错误注释。
论文信息
- 论文: https://arxiv.org/abs/2312.10160
- 代码: https://github.com/khuangaf/CHOCOLATE/
- 项目: https://khuangaf.github.io/CHOCOLATE
引用
如果您在工作中使用了 CHOCOLATE 数据集,请使用以下 BibTeX 引用论文:
@misc{huang-etal-2023-do, title = "Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning", author = "Huang, Kung-Hsiang and Zhou, Mingyang and Chan, Hou Pong and Fung, Yi R. and Wang, Zhenhailong and Zhang, Lingyu and Chang, Shih-Fu and Ji, Heng", year={2023}, eprint={2312.10160}, archivePrefix={arXiv}, primaryClass={cs.CL} }




