Chart Question Answering from Real-World Analytical Narratives

We present a new dataset for chart question answering (CQA) constructed from visualization notebooks. The dataset features real-world, multi-view charts paired with natural language questions grounded in analytical narratives. Unlike prior benchmarks, our data reflects ecologically valid reasoning workflows. Benchmarking state-of-the-art multimodal large language models reveals a significant performance gap, with GPT-4.1 achieving an accuracy of 69.3%, underscoring the challenges posed by this more authentic CQA setting.

@article{hutchinson2025_2507.01627,
  title={ Chart Question Answering from Real-World Analytical Narratives },
  author={ Maeve Hutchinson and Radu Jianu and Aidan Slingsby and Jo Wood and Pranava Madhyastha },
  journal={arXiv preprint arXiv:2507.01627},
  year={ 2025 }
}