MisVisFix: An Interactive Dashboard for Detecting, Explaining & Correcting Misleading Visualizations

Abstract: Misleading visualizations pose a significant challenge to accurate data interpretation. While recent research has explored the use of Large Language Models (LLMs) for detecting such misinformation, practical tools that also support explanation and correction remain limited. We present MisVisFix, an interactive dashboard that leverages both Claude and GPT models to support the full workflow of detecting, explaining, and correcting misleading visualizations. MisVisFix correctly identifies 96% of visualization issues and addresses all 74 known visualization misinformation types, classifying them as major, minor, or potential concerns. It provides detailed explanations, actionable suggestions, and automatically generates corrected charts. An interactive chat interface allows users to ask about specific chart elements or request modifications. The dashboard adapts to newly emerging misinformation strategies through targeted user interactions. User studies with visualization experts and developers of fact-checking tools show that MisVisFix accurately identifies issues and offers useful suggestions for improvement. By transforming LLM-based detection into an accessible, interactive platform, MisVisFix advances visualization literacy and supports more trustworthy data communication.

Teaser: Shown here is the MisVisFix interactive dashboard:

Panel A displays the original misleading visualization with interactive issue localization, where hovering over identified issues highlights the corresponding problematic regions directly on the chart. Panels B and C show corrected versions generated by Claude and GPT, enabling side-by-side comparison. Panel D allows users to upload the original dataset to improve accuracy when data extraction fails. Panels E and F list detected issues from GPT and Claude, categorized by severity. Panel G contains the interactive chat, where users can request modifications and view updated visualizations.

Video: Watch it to get a quick overview how a user would detect and fix misleading visualizations with MisVisFix:

Paper: A. Kumar, K. Mueller, “MisVisFix: An Interactive Dashboard for Detecting, Explaining, and Correcting Misleading Visualizations using Large Language Models,” IEEE Transactions on Visualization and Computer Graphics, 2026. PDF

Companion Paper: See also A. Kumar, M. Tarun, K. Mueller, “Charts-of-Thought: Enhancing LLM Visualization Literacy Through Structured Data Extraction,” IEEE Transactions on Visualization and Computer Graphics, 2026. This paper outlines in detail how MisVisFix decodes the visualization images. PDF

Funding: NSF grant NRT-HDR 2125295