Overview

Chart understanding studies how AI can interpret visualizations, from reading axes, legends, and plotted values to answering questions, comparing charts, and summarizing findings. Common approaches combine vision-language models with OCR, structured chart representations, visual grounding, and tools such as code execution; training often uses synthetic charts alongside real examples. Benchmarks increasingly test not only question answering but also data extraction, chart editing, dynamic interactions, and specialized settings such as scientific and financial figures. Models have improved, but reliable numerical reading, evidence-grounded reasoning, and robustness to dense or unfamiliar charts remain open challenges.

Latest papers

CardsList

63 papers2 papers in the last four weeks, down 71% on the four weeks before. 0.0% of all new papers.

  1. Stress Testing a Multimodal Large Language Model Grading Assistant on Kinematics Graph Reading

    Nov 17, 2026Ons Zammel, Carlos Soares, Flávia Carvalhido +1Automated GradingMLLM Evaluation

  2. ChartGalaxy++: A Richly Annotated Dataset for Chart Understanding and Generation

    Nov 11, 2026Duan Li, Zheng Wang, Jiangning Zhu +2Chart UnderstandingData Visualization

  3. OCRia-1 Technical Report

    Oct 22, 2026Aman Rangapur, Antonio Jimeno Yepes, Daniel Bustamante +4Document ParsingDocument Image Understanding

  4. Code-Interactive Visual Reasoning for Financial Candlestick Understanding

    Oct 12, 2026Chenxi Zhang, Youwei Pang, Xiaoqi Zhao +4Chart QAChart Understanding

  5. DataVista: Diagnosing Multimodal LLMs on Data Video Understanding

    Oct 8, 2026Yupeng Xie, Zhenyang Wang, Jiayi Zhu +4Video UnderstandingMultimodal Large Language Models

  6. Recursive Self-Improvement in Unified Multimodal Models

    Oct 2, 2026Huijuan Wang, Chufan Shi, Cheng Yang +3Unified Multimodal ModelsChart Understanding

  7. ChartDensity-Bench: Benchmarking MLLMs for Numerical Data Reconstruction under Visual Density

    Sep 30, 2026Xinhe Wu, Yadong JinMultimodal RobustnessChart Data Extraction

  8. LegendBench: A Diagnostic Benchmark for Legend Understanding with Counterfactual Interventions

    Sep 21, 2026Xinnuo Zhang, Zhike Tang, Jing Xu +2VLM EvaluationCounterfactual Evaluation of VLMs

  9. Monitorable Chart Reasoning Agents via Verifiable Process Rewards

    Sep 21, 2026Sanchit Sinha, Oana Frunza, Kashif Rasul +1AI Agent MonitoringReinforcement Learning with Verifiable Rewards

  10. LinePilot Digitizer: Line-Plot Recovery with Manual and Automatic Calibration

    Sep 16, 2026Fengbo Ma, Rayan Akhtar, Aakash H. Joshi +5Chart Data ExtractionChart Understanding

  11. Charts Are Beyond Pixels: Probing for Layer-Wise Chart Understanding and Editing

    Sep 8, 2026Xiaochuan Zhong, Yifan Hou, Chenxi Pang +1VLM EvaluationChart QA

  12. Structure-Token Evidence-Anchored Reasoning for Scientific Chart Understanding

    Sep 7, 2026Alberlucia Rafael Soarez, Camila Ferreira, Daniel Kim +2Chart UnderstandingChart QA

  13. DVBench: Benchmarking MLLMs for Understanding Dynamic Charts and Narratives in Data Videos

    Aug 30, 2026Bomiao Wang, Zekai Shao, Jiexiang Lan +3Video UnderstandingVideo-Language Model Evaluation

  14. Chart2SVG: Editable SVG Generation from Raster Chart Images

    Aug 27, 2026Jinning Cui, Lu Chen, Haoyan Shi +5Image VectorizationVector Graphics Generation

  15. VizAnchor: Decoding Manipulation Intent from Tampering Visualizations via Dual-Anchor Reasoning

    Aug 25, 2026Xiaotian Zhang, Huayuan Ye, Haiyang Zhang +3Data VisualizationChart Understanding

  16. KMGen: A Skill-based Approach for Synthetic Individual Patient Data Generation

    Aug 23, 2026Jalen Jiang, Chufan Gao, Ethan Rasmussen +2Synthetic Clinical Data GenerationSynthetic Data Generation

  17. Think with Structured Grounding: Perceptual Reinforcement Learning for Chart and Visual-Tabular Understanding

    Aug 23, 2026Changjiang Jiang, Qiannian Zhao, Lei Xin +3Visually Grounded ReasoningFine-Grained Visual Perception

  18. ChartProbe: A Diagnostic Study on Visual Reasoning through Perception, Grounding, and Simple Reasoning

    Aug 13, 2026Mahsa Khoshnoodi, Sarah Adel BargalChart UnderstandingChart QA

  19. Same Chart, Different Story: Bias in Vision-Language Chart Interpretation

    Aug 12, 2026Mizanur Rahman, Huan Wu, Arash Asgari +2Cultural Bias in VLMsDemographic Bias in VLMs

  20. Chartography: A Benchmark for Professional Chart Understanding

    Aug 11, 2026Suhaas Garre, Chris Mutty, Sushant Mehta +1Data VisualizationChart QA

  21. ChartAnno: Benchmarking Multimodal Large Language Models for Chart Annotation Generation

    Aug 4, 2026Zhenghan Chen, Zekai Shao, Lidan Tan +10Data VisualizationMultimodal Large Language Models

  22. Do Maps Still Matter for Machines: Revisiting the Role of Choropleth Maps in Foundation Model Spatial Understanding

    Jul 20, 2026Zhiwei Wei, Yonghe Sun, Zhenjia Liu +5Data VisualizationSpatial Reasoning Benchmarks

  23. Attention-Guided Saliency Maps for Interpreting Visualization Literacy in VLMs

    Jul 17, 2026Maeve Hutchinson, Abderrahmane Wassim Mehdaoui, Pranava MadhyasthaData VisualizationVisual Attention

  24. A Multimodal Reasoning Typology for Grounding Chart-Image Coherence in Science Communication

    Jul 6, 2026Avina Nakarmi, Sohom Sen, Xun Song +2Multimodal GroundingScientific Communication

  25. What You See Is What You Get: Observation-Aligned Supervision for Chart-to-Code Generation

    Jul 6, 2026Tianhao Niu, Qingfu Zhu, Wanxiang CheData VisualizationChart-to-Code Generation

  26. Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework

    Jun 29, 2026Yuchen He, Peizhi Ying, Liqi Cheng +4Document Information ExtractionMultimodal Large Language Models

  27. ChartLens: A Dual-Branch Framework for Chart Data Correction and Factual Summary Refinement

    Jun 9, 2026Hao Liu, Ruping Cao, Kun Wang +4Document Information ExtractionChart Data Extraction