InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts

TL;DR

This paper introduces InfoChartQA, a comprehensive benchmark for evaluating multimodal large language models on infographic chart understanding, emphasizing visual recognition and reasoning with paired plain and infographic charts.

Contribution

It provides a new dataset with paired charts and visual-element questions, enabling detailed evaluation and analysis of MLLMs' capabilities in infographic comprehension.

Findings

20 MLLMs show significant performance drops on infographic charts.

Performance is especially poor on visual-element questions involving metaphors.

Paired charts facilitate detailed error analysis and model improvement insights.

Abstract

Understanding infographic charts with design-driven visual elements (e.g., pictograms, icons) requires both visual recognition and reasoning, posing challenges for multimodal large language models (MLLMs). However, existing visual-question answering benchmarks fall short in evaluating these capabilities of MLLMs due to the lack of paired plain charts and visual-element-based questions. To bridge this gap, we introduce InfoChartQA, a benchmark for evaluating MLLMs on infographic chart understanding. It includes 5,642 pairs of infographic and plain charts, each sharing the same underlying data but differing in visual presentations. We further design visual-element-based questions to capture their unique visual designs and communicative intent. Evaluation of 20 MLLMs reveals a substantial performance decline on infographic charts, particularly for visual-element-based questions related to metaphors. The paired infographic and plain charts enable fine-grained error analysis and ablation studies, which highlight new opportunities for advancing MLLMs in infographic chart understanding. We release InfoChartQA at https://github.com/CoolDawnAnt/InfoChartQA.