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

Azher Ahmed Efat, Seok Hwan Song, Wallapak Tavanapong
4/23/2026
cs.CLcs.AIcs.CV

No confident code implementation found for this paper. 1 possible match can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning

87% match1 repo762024

ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering

86% match1 repo222024

Do LLMs Work on Charts? Designing Few-Shot Prompts for Chart Question Answering and Summarization

86% match2023

MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning

85% match1 repo952023

MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems

85% match1 repo132024

ChartM$^3$: A Multi-Stage Code-Driven Pipeline for Constructing Multi-Dimensional and Multi-Step Visual Reasoning Data in Chart Comprehension

84% match2025

Cite this paper

@article{efat2026beyond,
  title  = {Beyond Single Plots: A Benchmark for Question Answering on Multi-Charts},
  author = {Azher Ahmed Efat and Seok Hwan Song and Wallapak Tavanapong},
  year   = {2026},
  eprint = {2604.21344},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2604.21344v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2604.21344.svg)](https://codeofpaper.com/paper/2604.21344)

Discussion