PulseAugur
中
实时 08:58:08
English(EN) TETHER: Training-Free, Elastic, ToC-Anchored Hierarchy Extraction and Recovery in Design-Driven Long Documents

TETHER框架利用目录先验信息提取文档层级

研究人员开发了TETHER,一个新颖的框架,旨在从长而复杂的文档中提取层级结构,而无需进行预先训练。TETHER利用目录(ToC)作为结构先验,使用大型多模态模型(LMM)构建文档骨架,然后将内容块与该骨架对齐。这种方法在各种文档类型(包括ESG报告和产品手册)的零样本层级恢复方面展现了最先进的性能,同时显著减少了令牌使用量并提高了处理速度。 AI

影响 该框架可以显著改善LLM处理和理解长文档的方式,增强其在研究和分析中的效用。

排序理由 该集群包含一篇详细介绍新文档分析框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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

TETHER框架利用目录先验信息提取文档层级

本文如何被排名

Signal score
19 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍新文档分析框架的研究论文。[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, infra
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
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Yu Zou, Yan Chen, Jialei Zeng, Xiaorui Zhou, Aixi Zhong, Qi Zhou, Haoran You, Ke Jiang, Changyu Hu ·

    TETHER:无训练、弹性、以ToC为锚点的设计驱动长文档层级提取与恢复

    arXiv:2611.24960v1 Announce Type: new Abstract: Converting complex documents into structured knowledge constitutes the critical infrastructure urgently required for deploying Large Language Models (LLMs) in downstream research. However, blind to the Table of Contents (ToC) as a m…