Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910018492694528 |
|---|---|
| author | Yi, Zhihang Zhao, Jian Lv, Jiancheng Wang, Tao |
| author_facet | Yi, Zhihang Zhao, Jian Lv, Jiancheng Wang, Tao |
| contents | 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 revolutionized this domain, yet the landscape of MLLM-based chart analysis remains fragmented and lacks systematic organization. This survey provides a comprehensive roadmap of this nascent frontier by structuring the domain's core components. We begin by analyzing the fundamental challenges of fusing visual and linguistic information in charts. We then categorize downstream tasks and datasets, introducing a novel taxonomy of canonical and non-canonical benchmarks to highlight the field's expanding scope. Subsequently, we present a comprehensive evolution of methodologies, tracing the progression from classic deep learning techniques to state-of-the-art MLLM paradigms that leverage sophisticated fusion strategies. By critically examining the limitations of current models, particularly their perceptual and reasoning deficits, we identify promising future directions, including advanced alignment techniques and reinforcement learning for cognitive enhancement. This survey aims to equip researchers and practitioners with a structured understanding of how MLLMs are transforming chart information fusion and to catalyze progress toward more robust and reliable systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10138 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement Yi, Zhihang Zhao, Jian Lv, Jiancheng Wang, Tao Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning 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 revolutionized this domain, yet the landscape of MLLM-based chart analysis remains fragmented and lacks systematic organization. This survey provides a comprehensive roadmap of this nascent frontier by structuring the domain's core components. We begin by analyzing the fundamental challenges of fusing visual and linguistic information in charts. We then categorize downstream tasks and datasets, introducing a novel taxonomy of canonical and non-canonical benchmarks to highlight the field's expanding scope. Subsequently, we present a comprehensive evolution of methodologies, tracing the progression from classic deep learning techniques to state-of-the-art MLLM paradigms that leverage sophisticated fusion strategies. By critically examining the limitations of current models, particularly their perceptual and reasoning deficits, we identify promising future directions, including advanced alignment techniques and reinforcement learning for cognitive enhancement. This survey aims to equip researchers and practitioners with a structured understanding of how MLLMs are transforming chart information fusion and to catalyze progress toward more robust and reliable systems. |
| title | Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2602.10138 |