2025/03/25 by Kai Nylund, Jennifer Mankoff, Venkatesh Potluri · 2 voices · 8 citations
Computer Science · #Chart #Computer science #Explainable Artificial Intelligence (XAI) #Information retrieval #Machine Learning and Data Classification #Machine learning #Merge (version control) #Parsing #Programming language #Python (programming language) #Software Engineering Research #Statistics #Univariate
paper · pdf · doi:10.1111/cgf.70119
published in Computer Graphics Forum 44(3) (Wiley)
openalex publication_date 2025/05/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.