English(EN) Capability-Routed Visual Retrieval and Evidence Threading for Long-Context Document Question Answering

新系统通过视觉检索和证据链构建增强文档问答能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员开发了一种新颖的长上下文文档问答系统，特别适用于包含图表和信息图等视觉元素的文档。该系统名为VisRAG-Ret，利用冻结的Qwen2.5-VL-7B-Instruct模型，并包含三个新模块：一个能力感知视觉路由器（CAVR）用于分类页面类型，一个弱到强页面选择（WSPS）机制用于提炼答案可得性，以及一个视觉证据链（VET）用于为生成器创建布局锚定的路径。这种方法显著提高了在DocVQA、ChartQA和MMLongBench-Doc等各种文档视觉问答基准测试上的性能。 AI

影响提高了视觉文档问答任务的准确性，可能有助于分析复杂的报告和信息图。

排序理由该项目是一篇研究论文，详细介绍了一种新的文档问答系统和方法论。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目是一篇研究论文，详细介绍了一种新的文档问答系统和方法论。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Amirul Rahman, Aisha Karim, Kenji Nakamura, Yi-Fan Ng · 2026-09-15 04:00

面向长上下文文档问答的面向能力的视觉检索与证据链构建

arXiv:2609.13268v1 Announce Type: new Abstract: Annual reports, diligence packs, and infographic dashboards bury numbers in page images: axes, cell grids, and footnotes that OCR pipelines flatten and that page-level visual retrievers still treat as interchangeable in-context exam…

本文如何被排名

报道来源 [1]

面向长上下文文档问答的面向能力的视觉检索与证据链构建

相关实体

相关话题