针对图表类多模态问答，构建了首个系统性评测基准。
Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation Framework
- 通过关键点提取与跨模态验证生成高质量评测数据
- 发现当前模型在图表理解上正确率仅58.19%，覆盖率73.87%
- 适合关注多模态推理、图表理解的开发者和研究者
多模态检索增强生成（MRAG）通过引入外部知识提升推理能力，但现有评测主要聚焦简单图文交互，忽视真实场景中常见的图表等复杂视觉格式。本文提出新任务‘基于图表的MRAG’，并设计CHARGE框架，通过结构化关键点提取、跨模态验证与关键点驱动生成，半自动构建高质量评测样本。结合专家验证，构建了涵盖8个领域、4,738个问答对的Chart-MRAG Bench。评估揭示三大局限：统一多模态嵌入检索在图表场景表现不佳；即使使用真值检索，顶尖多模态大模型正确率仅为58.19%，覆盖率73.87%；模型普遍存在文本优先于视觉的模态偏差。相关代码与数据集已开源。
原文摘要 · Abstract (English)
Multimodal Retrieval-Augmented Generation (MRAG) enhances reasoning capabilities by integrating external knowledge. However, existing benchmarks primarily focus on simple image-text interactions, overlooking complex visual formats like charts that are prevalent in real-world applications. In this work, we introduce a novel task, Chart-based MRAG, to address this limitation. To semi-automatically generate high-quality evaluation samples, we propose CHARt-based document question-answering GEneration (CHARGE), a framework that produces evaluation data through structured keypoint extraction, crossmodal verification, and keypoint-based generation. By combining CHARGE with expert validation, we construct Chart-MRAG Bench, a comprehensive benchmark for chart-based MRAG evaluation, featuring 4,738 question-answering pairs across 8 domains from real-world documents. Our evaluation reveals three critical limitations in current approaches: (1) unified multimodal embedding retrieval methods struggles in chart-based scenarios, (2) even with ground-truth retrieval, state-of-the-art MLLMs achieve only 58.19% Correctness and 73.87% Coverage scores, and (3) MLLMs demonstrate consistent text-over-visual modality bias during Chart-based MRAG reasoning. The CHARGE and Chart-MRAG Bench are released at https://github.com/Nomothings/CHARGE.git.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。