Infogen: Generating Complex Statistical Infographics from Documents
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915413374271488 |
|---|---|
| author | Ghosh, Akash Garimella, Aparna Ramu, Pritika Bandyopadhyay, Sambaran Saha, Sriparna |
| author_facet | Ghosh, Akash Garimella, Aparna Ramu, Pritika Bandyopadhyay, Sambaran Saha, Sriparna |
| contents | Statistical infographics are powerful tools that simplify complex data into visually engaging and easy-to-understand formats. Despite advancements in AI, particularly with LLMs, existing efforts have been limited to generating simple charts, with no prior work addressing the creation of complex infographics from text-heavy documents that demand a deep understanding of the content. We address this gap by introducing the task of generating statistical infographics composed of multiple sub-charts (e.g., line, bar, pie) that are contextually accurate, insightful, and visually aligned. To achieve this, we define infographic metadata that includes its title and textual insights, along with sub-chart-specific details such as their corresponding data and alignment. We also present Infodat, the first benchmark dataset for text-to-infographic metadata generation, where each sample links a document to its metadata. We propose Infogen, a two-stage framework where fine-tuned LLMs first generate metadata, which is then converted into infographic code. Extensive evaluations on Infodat demonstrate that Infogen achieves state-of-the-art performance, outperforming both closed and open-source LLMs in text-to-statistical infographic generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20046 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Infogen: Generating Complex Statistical Infographics from Documents Ghosh, Akash Garimella, Aparna Ramu, Pritika Bandyopadhyay, Sambaran Saha, Sriparna Computation and Language Statistical infographics are powerful tools that simplify complex data into visually engaging and easy-to-understand formats. Despite advancements in AI, particularly with LLMs, existing efforts have been limited to generating simple charts, with no prior work addressing the creation of complex infographics from text-heavy documents that demand a deep understanding of the content. We address this gap by introducing the task of generating statistical infographics composed of multiple sub-charts (e.g., line, bar, pie) that are contextually accurate, insightful, and visually aligned. To achieve this, we define infographic metadata that includes its title and textual insights, along with sub-chart-specific details such as their corresponding data and alignment. We also present Infodat, the first benchmark dataset for text-to-infographic metadata generation, where each sample links a document to its metadata. We propose Infogen, a two-stage framework where fine-tuned LLMs first generate metadata, which is then converted into infographic code. Extensive evaluations on Infodat demonstrate that Infogen achieves state-of-the-art performance, outperforming both closed and open-source LLMs in text-to-statistical infographic generation. |
| title | Infogen: Generating Complex Statistical Infographics from Documents |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.20046 |