English(EN) EviProp: Seeded Relevance Diffusion on Chunk-Page Graphs for Long Multimodal Document Retrieval

EviProp 方法通过图扩散改进长文档检索

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-08 03:25

研究人员开发了 EviProp，一种从长而富含视觉信息的文档中检索相关页面的新方法。与现有独立评估页面相关性的方法不同，EviProp 将文档建模为多模态的块-页图。它使用种子相关性扩散，结合查询-页面相似度与块级信号来提高检索准确性。在基准数据集上的实验表明，EviProp 的性能优于传统方法，并能带来更好的下游问答性能。 AI

影响提高了复杂多模态文档的检索准确性，可能改进依赖文档理解的 AI 系统。

排序理由这是一篇描述新文档检索方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.IR (Information Retrieval) 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇描述新文档检索方法的学术论文。[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, other; 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: 99 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Guohang Yan · 2026-06-08 03:25

EviProp：基于块-页图的种子相关性扩散用于长多模态文档检索

Retrieving evidence pages from visually rich long documents is a key challenge in document question answering. Existing page-level visual retrievers operate under an independent matching paradigm: each page is scored in isolation based on query-page similarity. This paradigm can …

本文如何被排名

报道来源 [1]

EviProp：基于块-页图的种子相关性扩散用于长多模态文档检索

相关实体

相关话题