Beyond Single Plots: A Benchmark for Question Answering on Multi-Charts
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908989130801152 |
|---|---|
| author | Efat, Azher Ahmed Song, Seok Hwan Tavanapong, Wallapak |
| author_facet | Efat, Azher Ahmed Song, Seok Hwan Tavanapong, Wallapak |
| contents | Charts are widely used to present complex information. Deriving meaningful insights in real-world contexts often requires interpreting multiple related charts together. Research on understanding multi-chart images has not been extensively explored. We introduce PolyChartQA, a mid-scale dataset specifically designed for question answering over multi-chart images. PolyChartQA comprises 534 multi-chart images (with a total of 2,297 sub-charts) sourced from peer-reviewed computer science research publications and 2,694 QA pairs. We evaluate the performance of nine state-of-the-art Multimodal Language Models (MLMs) on PolyChartQA across question type, difficulty, question source, and key structural characteristics of multi-charts. Our results show a 27.4% LLM-based accuracy (L-Accuracy) drop on human-authored questions compared to MLM-generated questions, and a 5.39% L-accuracy gain with our proposed prompting method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_21344 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Single Plots: A Benchmark for Question Answering on Multi-Charts Efat, Azher Ahmed Song, Seok Hwan Tavanapong, Wallapak Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Multiagent Systems Charts are widely used to present complex information. Deriving meaningful insights in real-world contexts often requires interpreting multiple related charts together. Research on understanding multi-chart images has not been extensively explored. We introduce PolyChartQA, a mid-scale dataset specifically designed for question answering over multi-chart images. PolyChartQA comprises 534 multi-chart images (with a total of 2,297 sub-charts) sourced from peer-reviewed computer science research publications and 2,694 QA pairs. We evaluate the performance of nine state-of-the-art Multimodal Language Models (MLMs) on PolyChartQA across question type, difficulty, question source, and key structural characteristics of multi-charts. Our results show a 27.4% LLM-based accuracy (L-Accuracy) drop on human-authored questions compared to MLM-generated questions, and a 5.39% L-accuracy gain with our proposed prompting method. |
| title | Beyond Single Plots: A Benchmark for Question Answering on Multi-Charts |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2604.21344 |