arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2507.20145cs.CLcs.AI
收藏

面向长文档理解的多智能体交互式问题生成框架

Multi-Agent Interactive Question Generation Framework for Long Document Understanding

Kesen Wang, Daulet Toibazar, Abdulrahman Alfulayt, Abdulaziz S. Albadawi, Ranya A. Alkahtani, Asma A. Ibrahim, Haneen A. Alhomoud, Sherif Mohamed, Pedro J. Moreno

AI总结:

针对长文档理解中细粒度英阿训练数据稀缺、人工标注昂贵的问题,提出全自动多智能体交互式框架生成跨领域单页与多页问答,并构建 AraEngLongBench 验证其对开源及闭源 LVLM 的挑战性。

摘要:

在具有复杂版式的长上下文场景中,文档理解(Document Understanding,DU)仍是视觉-语言研究中的一项重大挑战。尽管大型视觉-语言模型(Large Vision-Language Models,LVLMs)擅长短上下文 DU 任务,但它们在长上下文设置下的性能会下降。一个关键限制是细粒度训练数据的稀缺,尤其是在阿拉伯语等低资源语言方面。现有最先进技术严重依赖人工标注,成本高昂且效率低下。我们提出了一种全自动的多智能体交互式框架,以高效生成长上下文问题。我们的方法能够针对涵盖数百页、跨越多个不同领域的大量英文和阿拉伯文文档,高效生成高质量的单页和多页问题。这促进了具有更强长上下文理解能力的 LVLMs 的开发。本文的实验结果表明,我们生成的英文和阿拉伯文问题(AraEngLongBench)对主流开源和闭源 LVLMs 都具有相当大的挑战性。本文提出的代码和数据可在 https://github.com/wangk0b/Multi_Agentic_QA_Long_Doc.git 获取。示例问答(Question and Answer,QA)对和结构化系统提示可在附录中找到。

英文摘要:

Document Understanding (DU) in long-contextual scenarios with complex layouts remains a significant challenge in vision-language research. Although Large Vision-Language Models (LVLMs) excel at short-context DU tasks, their performance declines in long-context settings. A key limitation is the scarcity of fine-grained training data, particularly for low-resource languages such as Arabic. Existing state-of-the-art techniques rely heavily on human annotation, which is costly and inefficient. We propose a fully automated, multi-agent interactive framework to generate long-context questions efficiently. Our approach efficiently generates high-quality single- and multi-page questions for extensive English and Arabic documents, covering hundreds of pages across diverse domains. This facilitates the development of LVLMs with enhanced long-context understanding ability. Experimental results in this work have shown that our generated English and Arabic questions (\textbf{AraEngLongBench}) are quite challenging to major open- and close-source LVLMs. The code and data proposed in this work can be found in https://github.com/wangk0b/Multi_Agentic_QA_Long_Doc.git. Sample Question and Answer (QA) pairs and structured system prompts can be found in the Appendix.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑