Home

Awesome

Awesome Chart Understanding

Awesome PRWelcome arXiv

A curated list of recent and past chart understanding work based on our survey paper: From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models.

The repository will be continuously updated 📝. Don't forget to hit the ⭐️ and stay tuned!

If you find this resource beneficial for your research, please do not hesitate to cite the paper referenced in the Citation section. Thank you!

Table of Contents

Tasks and Datasets

Chart Question Answering

Factoid Questions

Long-form Questions

Chart Captioning (Summarization)

Factual Inconsistency Detection for Chart Captioning

Chart Fact-checking

Chart Caption Factual Error Correction

Chart to Code

Methods

Classification-based Methods

Fixed Output Vocab

Dynamic Encoding

Pre-trained

Generation-based Methods

Without Pre-training

Saad Obaid ul Islam, Iza Škrjanec, Ondřej Dušek, Vera Demberg <img src='https://img.shields.io/badge/INLG-2023-yellow'> <a href='https://aclanthology.org/2023.inlg-main.30/'><img src='https://img.shields.io/badge/PDF-blue'></a> <a href='[https://github.com/JasonObeid/Chart2Text](https://github.com/WorldHellow/Hallucinations-C2T)'><img src='https://img.shields.io/badge/Model-green'></a>

Pre-trained

Tool Augmentation

Large Vision-language Models

Tailored for Chart Understanding

General-purpose

Evaluation

Faithfulness/ Factuality

Analysis

Citation

@misc{huang-etal-2024-chart,
    title = "From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models",
    author = "Huang, Kung-Hsiang and Chan, Hou Pong and Fung, Yi R. and Qiu, Haoyi and Zhou, Mingyang and Joty, Shafiq and Chang, Shih-Fu and Ji, Heng",
    year={2024},
    eprint={2403.12027},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}