MatplotAlt: A Python Library for Adding Alt Text to Matplotlib Figures in Computational Notebooks

@XXXXX{Nylund2025MatplotAltPythonLibrary,
  author    = {Kai Nylund, Jennifer Mankoff, Venkatesh Potluri},
  VENUE     = {Computer Graphics Forum—EuroVis/CGF},
  title     = {MatplotAlt: A Python Library for Adding Alt Text to Matplotlib Figures in Computational Notebooks},
  year      = {2025},
  note      = {XXX YYYY. Preprint at \url{https://arxiv.org/pdf/2503.20089}. Supplemental material at \url{}.},
  number    = {},
  pages     = {e70119},
  volume    = {44},
  abstract  = {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.},
  articleno = {},
  doi       = {https://doi.org/10.1111/cgf.70119},
  series   = {EuroVis/CGF},
}