ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909573380571136 |
|---|---|
| author | Masry, Ahmed Islam, Mohammed Saidul Ahmed, Mahir Bajaj, Aayush Kabir, Firoz Kartha, Aaryaman Laskar, Md Tahmid Rahman Rahman, Mizanur Rahman, Shadikur Shahmohammadi, Mehrad Thakkar, Megh Parvez, Md Rizwan Hoque, Enamul Joty, Shafiq |
| author_facet | Masry, Ahmed Islam, Mohammed Saidul Ahmed, Mahir Bajaj, Aayush Kabir, Firoz Kartha, Aaryaman Laskar, Md Tahmid Rahman Rahman, Mizanur Rahman, Shadikur Shahmohammadi, Mehrad Thakkar, Megh Parvez, Md Rizwan Hoque, Enamul Joty, Shafiq |
| contents | Charts are ubiquitous, as people often use them to analyze data, answer questions, and discover critical insights. However, performing complex analytical tasks with charts requires significant perceptual and cognitive effort. Chart Question Answering (CQA) systems automate this process by enabling models to interpret and reason with visual representations of data. However, existing benchmarks like ChartQA lack real-world diversity and have recently shown performance saturation with modern large vision-language models (LVLMs). To address these limitations, we introduce ChartQAPro, a new benchmark that includes 1,341 charts from 157 diverse sources, spanning various chart types, including infographics and dashboards, and featuring 1,948 questions in various types, such as multiple-choice, conversational, hypothetical, and unanswerable questions, to better reflect real-world challenges. Our evaluations with 21 models show a substantial performance drop for LVLMs on ChartQAPro; e.g., Claude Sonnet 3.5 scores 90.5% on ChartQA but only 55.81% on ChartQAPro, underscoring the complexity of chart reasoning. We complement our findings with detailed error analyses and ablation studies, identifying key challenges and opportunities for advancing LVLMs in chart understanding and reasoning. We release ChartQAPro at https://github.com/vis-nlp/ChartQAPro. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05506 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering Masry, Ahmed Islam, Mohammed Saidul Ahmed, Mahir Bajaj, Aayush Kabir, Firoz Kartha, Aaryaman Laskar, Md Tahmid Rahman Rahman, Mizanur Rahman, Shadikur Shahmohammadi, Mehrad Thakkar, Megh Parvez, Md Rizwan Hoque, Enamul Joty, Shafiq Computation and Language Charts are ubiquitous, as people often use them to analyze data, answer questions, and discover critical insights. However, performing complex analytical tasks with charts requires significant perceptual and cognitive effort. Chart Question Answering (CQA) systems automate this process by enabling models to interpret and reason with visual representations of data. However, existing benchmarks like ChartQA lack real-world diversity and have recently shown performance saturation with modern large vision-language models (LVLMs). To address these limitations, we introduce ChartQAPro, a new benchmark that includes 1,341 charts from 157 diverse sources, spanning various chart types, including infographics and dashboards, and featuring 1,948 questions in various types, such as multiple-choice, conversational, hypothetical, and unanswerable questions, to better reflect real-world challenges. Our evaluations with 21 models show a substantial performance drop for LVLMs on ChartQAPro; e.g., Claude Sonnet 3.5 scores 90.5% on ChartQA but only 55.81% on ChartQAPro, underscoring the complexity of chart reasoning. We complement our findings with detailed error analyses and ablation studies, identifying key challenges and opportunities for advancing LVLMs in chart understanding and reasoning. We release ChartQAPro at https://github.com/vis-nlp/ChartQAPro. |
| title | ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.05506 |