mlsanityData to 7 Oct 2026

ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing

arXiv 2505.11935 ↗First posted 17 May 2025cs.CLcited by 28

On the map: Multimodal LLMs / vision-language models → Chart understanding and anomaly detection

Abstract (arXiv)

Although multimodal large language models (MLLMs) show promise in generating chart rendering code, editing charts via code presents a greater challenge. This task demands MLLMs to integrate chart understanding and reasoning capacities, which are labor-intensive. While many MLLMs claim such editing capabilities, current evaluations rely on limited case studies, highlighting the urgent need for a comprehensive evaluation framework. In this work, we propose textscChartEdit, a novel benchmark designed for chart editing tasks, featuring 1405 diverse editing instructions applied to 233 real-world charts, each manually annotated and validated for accuracy. Utilizing textscChartEdit, we evaluate the performance of 10 mainstream MLLMs across two types of experiments at both the code and chart levels. The results suggest that large-scale models can generate code to produce images that partially match the reference images. However, their ability to generate accurate edits according to the instructions remains limited. The state-of-the-art (SOTA) model achieves a score of only 59.96, highlighting significant challenges in precise modification. In contrast, small-scale models, including chart-domain models, struggle both with following editing instructions and generating overall chart images, underscoring the need for further development in this area. Code is available at https://github.com/xxlllz/ChartEdit.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 25 of its 42 references that are in the map. First posted on arXiv 17 May 2025.

Builds on

25 of 42 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation11 Jan
  2. 2024CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs26 Jun
  3. 2024ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation14 Jun
  4. 2024ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning19 Feb

Other references · 21

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  6. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  7. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  8. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  9. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  10. 2024A Survey on LLM-as-a-Judgecited by 1,384
  11. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  12. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,038
9 more
  1. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  2. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 545
  3. 2023VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Taskscited by 499
  4. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 484
  5. 2022DePlot: One-shot visual language reasoning by plot-to-table translationcited by 157
  6. 2024MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualizationcited by 98
  7. 2024RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesiscited by 55
  8. 2024Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedbackcited by 16
  9. 2024ChartReformer: Natural Language-Driven Chart Image Editingcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 17.

28 papers.

Sort:

By area:

  1. 2025ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLMcited by 36
  2. 2025Chart-R1: Chain-of-Thought Supervision and Reinforcement for Advanced Chart Reasonercited by 24
  3. 2025Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generationcited by 18
  4. 2025VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learningcited by 18
  5. 2025Enhancing Multimodal Continual Instruction Tuning with BranchLoRAcited by 14
  6. 2025ChartEditor: A Reinforcement Learning Framework for Robust Chart Editingcited by 9
  7. 2025Charts Are Not Images: On the Challenges of Scientific Chart Editingcited by 9
  8. 2025JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligencecited by 7
  9. 2026Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learningcited by 6
  10. 2025ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinementcited by 3
  11. 2026TangramPuzzle: Evaluating Multimodal Large Language Models with Compositional Spatial Reasoningcited by 3
  12. 2026ChartE3: A Comprehensive Benchmark for End-to-End Chart Editingcited by 3
16 more
  1. 2026OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Rewardcited by 3
  2. 2026ChartSync: A Benchmark for Visuo-Logical Cascading Chart Editingcited by 2
  3. 2025Learning Deliberately, Acting Intuitively: Unlocking Test-Time Reasoning in Multimodal LLMscited by 1
  4. 2026AnnoBench: A Benchmark for Visualization Annotation Generationcited by 1
  5. 2025Information-Theoretic Complementary Prompts for Improved Continual Text Classificationcited by 0
  6. 2026Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Modelscited by 0
  7. 2026ChartAnno: Benchmarking Multimodal Large Language Models for Chart Annotation Generationcited by 0
  8. 2026Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZcited by 0
  9. 2026Who Leads Now? Token-Level Modality Arbitration for Chart-to-Code Generationcited by 0
  10. 2026REChart: Reasoning-Efficient Chart Editing with Large Reasoning Modelscited by 0
  11. 2026Code as Representation: A Compilable Parsing Paradigm for Academic Documentscited by 0
  12. 2026EdiTikZ: Scientific Figure Editing from Revision Trajectoriescited by 0
  13. 2026Charts Are Beyond Pixels: Probing for Layer-Wise Chart Understanding and Editingcited by 0
  14. 2026Hyper-LLaVA: Hyperbolic Uncertainty-aware Modality-Balanced Routing for Multimodal Continual Instruction Tuningcited by 0
  15. 2026Point, Revise, Review: Grounded Agentic Analysis in Reactive Notebooks with marimo-lenscited by 0
  16. 2026ChartRevise: A Dataset and Evaluation Protocol for Exact Chart Editing via Codecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025ChartM3: Benchmarking Chart Editing with Multimodal Instructions
  2. 2026ChartEditBench: Evaluating Grounded Multi-Turn Chart Editing in Multimodal Language Models
  3. 2026ChartRevive: Reconstructing Data Visualizations from Chart Images Using MLLM ↗
  4. 2023ChartBench: A Benchmark for Complex Visual Reasoning in Charts
  5. 2025From Charts to Code: A Hierarchical Benchmark for Multimodal Models
  6. 2025START: Spatial and Textual Learning for Chart Understanding
  7. 2025Do MLLMs Really Understand the Charts?
  8. 2025ChartAnchor: Chart Grounding with Structural-Semantic Fidelity