Beyond Single Plots: A Benchmark for Question Answering on Multi-Charts

TL;DR

This paper introduces PolyChartQA, a new dataset for question answering on multi-chart images, highlighting the challenges and evaluating state-of-the-art models' performance in understanding complex visual data.

Contribution

The paper presents PolyChartQA, a benchmark dataset for multi-chart question answering, and assesses the performance of nine advanced multimodal language models on this task.

Findings

Models show a 27.4% accuracy drop on human-authored questions.

Prompting methods improve accuracy by 5.39%.

PolyChartQA enables evaluation of multi-chart understanding in AI models.

Abstract

Charts are widely used to present complex information. Deriving meaningful insights in real-world contexts often requires interpreting multiple related charts together. Research on understanding multi-chart images has not been extensively explored. We introduce PolyChartQA, a mid-scale dataset specifically designed for question answering over multi-chart images. PolyChartQA comprises 534 multi-chart images (with a total of 2,297 sub-charts) sourced from peer-reviewed computer science research publications and 2,694 QA pairs. We evaluate the performance of nine state-of-the-art Multimodal Language Models (MLMs) on PolyChartQA across question type, difficulty, question source, and key structural characteristics of multi-charts. Our results show a 27.4% LLM-based accuracy (L-Accuracy) drop on human-authored questions compared to MLM-generated questions, and a 5.39% L-accuracy gain with our proposed prompting method.