Deplot: One-shot visual language reasoning by plot-to-table translation

F Liu, JM Eisenschlos, F Piccinno, S Krichene… - arXiv preprint arXiv …, 2022 - arxiv.org
Visual language such as charts and plots is ubiquitous in the human world. Comprehending
plots and charts requires strong reasoning skills. Prior state-of-the-art (SOTA) models …

From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models

KH Huang, HP Chan, YR Fung, H Qiu, M Zhou… - arXiv preprint arXiv …, 2024 - arxiv.org
Data visualization in the form of charts plays a pivotal role in data analysis, offering critical
insights and aiding in informed decision-making. Automatic chart understanding has …

Scigraphqa: A large-scale synthetic multi-turn question-answering dataset for scientific graphs

S Li, N Tajbakhsh - arXiv preprint arXiv:2308.03349, 2023 - arxiv.org
In this work, we present SciGraphQA, a synthetic multi-turn question-answer dataset related
to academic graphs. SciGraphQA is 13 times larger than ChartVQA, the previously largest …

Multimodal automated fact-checking: A survey

M Akhtar, M Schlichtkrull, Z Guo, O Cocarascu… - arXiv preprint arXiv …, 2023 - arxiv.org
Misinformation is often conveyed in multiple modalities, eg a miscaptioned image.
Multimodal misinformation is perceived as more credible by humans, and spreads faster …

OneChart: Purify the Chart Structural Extraction via One Auxiliary Token

J Chen, L Kong, H Wei, C Liu, Z Ge, L Zhao… - arXiv preprint arXiv …, 2024 - arxiv.org
Chart parsing poses a significant challenge due to the diversity of styles, values, texts, and
so forth. Even advanced large vision-language models (LVLMs) with billions of parameters …

Chartcheck: An evidence-based fact-checking dataset over real-world chart images

M Akhtar, N Subedi, V Gupta, S Tahmasebi… - arXiv preprint arXiv …, 2023 - arxiv.org
Data visualizations are common in the real-world. We often use them in data sources such
as scientific documents, news articles, textbooks, and social media to summarize key …

ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning

A Masry, M Shahmohammadi, MR Parvez… - arXiv preprint arXiv …, 2024 - arxiv.org
Charts provide visual representations of data and are widely used for analyzing information,
addressing queries, and conveying insights to others. Various chart-related downstream …

DOMINO: A Dual-System for Multi-step Visual Language Reasoning

P Wang, O Golovneva, A Aghajanyan, X Ren… - arXiv preprint arXiv …, 2023 - arxiv.org
Visual language reasoning requires a system to extract text or numbers from information-
dense images like charts or plots and perform logical or arithmetic reasoning to arrive at an …

Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning? An Extensive Investigation into the Capabilities and Limitations of …

MS Islam, R Rahman, A Masry, MTR Laskar… - arXiv preprint arXiv …, 2024 - arxiv.org
Natural language is a powerful complementary modality of communication for data
visualizations, such as bar and line charts. To facilitate chart-based reasoning using natural …

Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA

Z Li, B Jasani, P Tang… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Understanding data visualizations like charts and plots requires reasoning about both visual
elements and numerics. Although strong in extractive questions current chart visual question …