EUVIMEDEUVIMED entdecken
Crossref

EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding

Muye Huang, Han Lai, Xinyu Zhang, Wenjun Wu, Jie Ma, Lingling Zhang, Jun Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (4) · 3680-3688

DOI: 10.1609/aaai.v39i4.32383 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Muye Huang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Chart understanding enables automated data analysis for humans, which requires models to achieve highly accurate visual comprehension. While existing Visual Language Models (VLMs) have shown progress in chart understanding, the lack of high-quality training data and comprehensive evaluation benchmarks hinders VLM chart comprehension. In this paper, we introduce EvoChart, a novel self-training method for generating synthetic chart data to enhance VLMs' capabilities in real-world chart comprehension. We also propose EvoChart-QA, a noval benchmark for measuring models' chart comprehension abilities in real-world scenarios. Specifically, EvoChart is a unique self-training data synthesis approach that simultaneously produces high-quality training corpus and a high-performance chart understanding model. EvoChart-QA consists of 650 distinct real-world charts collected from 140 different websites and 1,250 expert-curated questions that focus on chart understanding. Experimental results on various open-source and proprietary VLMs tested on EvoChart-QA demonstrate that even the best proprietary model, GPT-4o, achieves only 49.8% accuracy. Moreover, the EvoChart method significantly boosts the performance of open-source VLMs on real-world chart understanding tasks, achieving 54.2% accuracy on EvoChart-QA.

Zitieren

APA

Huang, M., Lai, H., Zhang, X., Wu, W., Ma, J., Zhang, L., & Liu, J. (2025). EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding. Proceedings of the AAAI Conference on Artificial Intelligence, 39(4), 3680-3688. https://doi.org/10.1609/aaai.v39i4.32383

Vancouver

Huang M, Lai H, Zhang X, Wu W, Ma J, Zhang L, et al. EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(4):3680-3688. doi:10.1609/aaai.v39i4.32383

BibTeX
@article{Huang2025,
  author = {Huang, Muye and Lai, Han and Zhang, Xinyu and Wu, Wenjun and Ma, Jie and Zhang, Lingling and Liu, Jun},
  title = {EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {4},
  pages = {3680--3688},
  doi = {10.1609/aaai.v39i4.32383}
}
Kostenlos starten →