Chart Question Answering from Real-World Analytical Narratives

Maeve Hutchinson, Radu Jianu, Aidan Slingsby, Jo Wood, Pranava Madhyastha

Keywords: Chart Question Answering, Multimodal Language Models, Visual Reasoning, Benchmark Dataset

TL;DR: We introduce a new chart question answering (CQA) dataset built from data visualization notebooks, featuring real-world, multi-view, and interactive charts grounded in analytical narratives.

Abstract: 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.

Archival Status: Archival

Paper Length: Short Paper (up to 4 pages of content)

Submission Number: 170