MatplotAlt: A Python Library for Adding Alt Text to Matplotlib Figures in Computational Notebooks
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_ | 1866917968366010368 |
|---|---|
| author | Nylund, Kai Mankoff, Jennifer Potluri, Venkatesh |
| author_facet | Nylund, Kai Mankoff, Jennifer Potluri, Venkatesh |
| contents | We present MatplotAlt, an open-source Python package for easily adding alternative text to Matplotlib figures. MatplotAlt equips Jupyter notebook authors to automatically generate and surface chart descriptions with a single line of code or command, and supports a range of options that allow users to customize the generation and display of captions based on their preferences and accessibility needs. Our evaluation indicates that MatplotAlt's heuristic and LLM-based methods to generate alt text can create accurate long-form descriptions of both simple univariate and complex Matplotlib figures. We find that state-of-the-art LLMs still struggle with factual errors when describing charts, and improve the accuracy of our descriptions by prompting GPT4-turbo with heuristic-based alt text or data tables parsed from the Matplotlib figure. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20089 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MatplotAlt: A Python Library for Adding Alt Text to Matplotlib Figures in Computational Notebooks Nylund, Kai Mankoff, Jennifer Potluri, Venkatesh Human-Computer Interaction H.5.2; K.3.1 We present MatplotAlt, an open-source Python package for easily adding alternative text to Matplotlib figures. MatplotAlt equips Jupyter notebook authors to automatically generate and surface chart descriptions with a single line of code or command, and supports a range of options that allow users to customize the generation and display of captions based on their preferences and accessibility needs. Our evaluation indicates that MatplotAlt's heuristic and LLM-based methods to generate alt text can create accurate long-form descriptions of both simple univariate and complex Matplotlib figures. We find that state-of-the-art LLMs still struggle with factual errors when describing charts, and improve the accuracy of our descriptions by prompting GPT4-turbo with heuristic-based alt text or data tables parsed from the Matplotlib figure. |
| title | MatplotAlt: A Python Library for Adding Alt Text to Matplotlib Figures in Computational Notebooks |
| topic | Human-Computer Interaction H.5.2; K.3.1 |
| url | https://arxiv.org/abs/2503.20089 |