paper-with-me

Papers

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

2026-06-29 · Yuchen He, Peizhi Ying, Liqi Cheng, Kuilin Peng, Yuan Tian, Dazhen Deng, Yingcai Wu arxiv

Chart data extraction, which reverse-engineers data tables from chart images, is essential for reproducibility, analysis, retrieval, and redesign. Existing interactive tools are reliable but tedious, and mixed-initiative systems, while more efficient, lack generalizability. Recent multimodal large language models (MLLMs) offer a unified interface for chart interpretation, yet their ability to extract accurate data tables, especially without visible labels, remains unclear. We build a benchmark featuring diverse real-world charts without data labels to evaluate this capability. Results show that, while current MLLMs reliably reconstruct table structures, they struggle with precise value recovery. To address this, we revisit chart data extraction from a human-centered perspective and argue that extraction should follow a progressive learning process similar to how people read charts. Our training framework substantially improves numerical accuracy, achieving state-of-the-art performance with a 7B-parameter model. A user study further shows that our model effectively supports mixed-initiative workflows for reliable chart data extraction.

📄 PDF Abstract BibTeX arXiv:2606.29808

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Chart-to-Experience: Benchmarking Multimodal LLMs for Predicting Experiential Impact of Charts

2025-05-23 · Seon Gyeom Kim, Jae Young Choi, Ryan Rossi, Eunyee Koh 외

The field of Multimodal Large Language Models (MLLMs) has made remarkable progress in visual understanding tasks, presenting a vast opportunity to predict the perceptual and emotional impact of charts. However, it also r…

Benchmarking

DEEPCHART: How Far are LLMs from Faithful Data-Science Chart Generation?

2026-08-27 · Jiahui tang, Kuicai Dong, Dexun Li, Hongchao Gu 외 arxiv

Faithful chart generation in real-world data-science workflows requires grounding visualizations in scattered evidence, computing chart-ready quantities, and rendering them accurately. Modern LLMs can produce visually pl…

CFBenchmark-MM: Chinese Financial Assistant Benchmark for Multimodal Large Language Model

2025-06-16 · Jiangtong Li, Yiyun Zhu, Dawei Cheng, Zhijun Ding 외

Multimodal Large Language Models (MLLMs) have rapidly evolved with the growth of Large Language Models (LLMs) and are now applied in various fields. In finance, the integration of diverse modalities such as text, charts,…

Decision MakingFinancial AnalysisLanguage ModelingLanguage Modelling+2

Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement

2026-02-08 · Zhihang Yi, Jian Zhao, Jiancheng Lv, Tao Wang arxiv

Chart understanding is a quintessential information fusion task, requiring the seamless integration of graphical and textual data to extract meaning. The advent of Multimodal Large Language Models (MLLMs) has revolutioni…

Reinforcement Learning

Format Matters: The Robustness of Multimodal LLMs in Reviewing Evidence from Tables and Charts

2025-11-13 · Xanh Ho, Yun-Ang Wu, Sunisth Kumar, Florian Boudin 외 arxiv

With the growing number of submitted scientific papers, there is an increasing demand for systems that can assist reviewers in evaluating research claims. Experimental results are a core component of scientific work, oft…

Multimodal Reasoning