arXiv cs.CL· Yufei Tong, Guanjie Cheng, Tianle Wu, Leilei Zhang, Hang Zheng, Peihan Wu, Jianwei Yin, Shuiguang Deng·· 13 小时前AI 评分24
长文档视觉问答的任务中心综述：分类体系、演进与未来方向
A Task-Centric Survey of Long-Document Visual Question Answering: Taxonomy, Evolution, and Future Directions
AI 导读
一篇综述将长文档视觉问答（VQA）拆解为文档解析、证据组织与检索、生成器组织与学习、评估四个环节，并为每个环节建立细粒度分类体系。时序分析显示，研究重心正从多模态内容理解转向充分高保真的证据获取与持续证据管理。未来方向包括证据充分性、可验证可纠正的理解与预算感知协调。
正文 · 原文
Abstract:Visual document understanding is essential for acquiring knowledge from visually rich documents and is attracting growing research interest. Existing surveys emphasize architectures or technical approaches, with limited attention to how task bottlenecks shape technical choices and research priorities. We present a task-centric survey that decomposes long-document visual question answering (VQA) into four components: document parsing, evidence organization and retrieval, generator organization and learning, and evaluation. For each, we develop a fine-grained taxonomy and trace motivations, technical responses, and cross-component connections. We focus on explicit retrieval while covering direct reading. Our temporal analysis traces expanding priorities from multimodal content understanding to sufficient, high-fidelity evidence acquisition and sustained evidence management. We outline future directions in evidence sufficiency, verifiable and correctable understanding, and budget-aware coordination, with an outlook on continual document understanding.
| Comments: | 26 pages, 9 figures, 6 tables |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.31385 [cs.CV] |
| (or arXiv:2610.31385v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31385 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yufei Tong [view email]
[v1]
Thu, 22 Oct 2026 14:52:47 UTC (34,016 KB)
来源：arXiv cs.CL · arxiv.org