Do you "see" what I "see"? A Multi-panel Visual Question Answer Dataset for Large Language Model Chart Analysis
cs.DL, cs.AI, cs.IR
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/ReadingTimeMachine/LLM_VQA_MultiPanel
Project page: https://chartinfo.github.io
Sources
- VQA: Visual Question Answering
- ChartCheck: Explainable Fact-Checking over Real-World Chart Images
- DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ
- Language Models are Few-Shot Learners
- ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts
- MapQA: A Dataset for Question Answering on Choropleth Maps
- In-Depth and In-Breadth: Pre-training Multimodal Language Models Customized for Comprehensive Chart Understanding
- MathWriting: A Dataset For Handwritten Mathematical Expression Recognition
- ChartQA-X: Generating Explanations for Visual Chart Reasoning
- SciCap: Generating Captions for Scientific Figures
- From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models
- EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding
- OpenCQA: Open-ended Question Answering with Charts
- A Diagram Is Worth A Dozen Images
- ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding
- SciGraphQA: A Large-Scale Synthetic Multi-Turn Question-Answering Dataset for Scientific Graphs
- ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation
- A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges
- MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering
- ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering