Chartbench: A benchmark for complex visual reasoning in charts

Z Xu, S Du, Y Qi, C Xu, C Yuan, J Guo - arxiv preprint arxiv:2312.15915, 2023 - arxiv.org
Multimodal Large Language Models (MLLMs) have demonstrated remarkable multimodal
understanding and generation capabilities. However, their understanding of synthetic charts …

Chartsumm: A comprehensive benchmark for automatic chart summarization of long and short summaries

R Rahman, R Hasan, AA Farhad, MTR Laskar… - arxiv preprint arxiv …, 2023 - arxiv.org
Automatic chart to text summarization is an effective tool for the visually impaired people
along with providing precise insights of tabular data in natural language to the user. A large …

AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks

O Moured, J Zhang, MS Sarfraz… - … Conference on Document …, 2024 - Springer
Chart summarization is a crucial task for blind and visually impaired individuals as it is their
primary means of accessing and interpreting graphical data. Crafting high-quality …

ChartThinker: A Contextual Chain-of-Thought Approach to Optimized Chart Summarization

M Liu, D Chen, Y Li, G Fang, Y Shen - arxiv preprint arxiv:2403.11236, 2024 - arxiv.org
Data visualization serves as a critical means for presenting data and mining its valuable
insights. The task of chart summarization, through natural language processing techniques …

Summaries as captions: Generating figure captions for scientific documents with automated text summarization

CY Huang, TY Hsu, R Rossi, A Nenkova, S Kim… - arxiv preprint arxiv …, 2023 - arxiv.org
Good figure captions help paper readers understand complex scientific figures.
Unfortunately, even published papers often have poorly written captions. Automatic caption …

Deep Learning-based Interactive Dashboard for Enhancing Online Classroom Experience through Student Emotion Analysis

P Ganesan, SK Jagatheesaperumal, I Gobhinath… - IEEE …, 2024 - ieeexplore.ieee.org
An interactive analytical dashboard that analyzes students' facial expressions during online
lectures is crucial for digital learning platforms. This research addresses the need for …

Tackling hallucinations in neural chart summarization

SOU Islam, I Škrjanec, O Dušek… - Proceedings of the 16th …, 2023 - aclanthology.org
Hallucinations in text generation occur when the system produces text that is not grounded
in the input. In this work, we tackle the problem of hallucinations in neural chart …

Bengali ChartSumm: A Benchmark Dataset and Study on Feasibility of Large Language Models on Bengali Chart to Text Summarization

NA Tanjila, AS Poushi, SA Farhan… - Proceedings of the …, 2025 - aclanthology.org
In today's data-driven world, effectively organizing and presenting data is challenging,
particularly for non-experts. While tabular formats structure data, they often lack intuitive …

Tackling Hallucinations in Neural Chart Summarization

I Škrjanec, O Dušek, V Demberg - arxiv preprint arxiv:2308.00399, 2023 - arxiv.org
Hallucinations in text generation occur when the system produces text that is not grounded
in the input. In this work, we tackle the problem of hallucinations in neural chart …

Faithful Chart Summarization with ChaTS-Pi

S Krichene, F Piccinno, F Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
Chart-to-summary generation can help explore data, communicate insights, and help the
visually impaired people. Multi-modal generative models have been used to produce fluent …