English(EN) Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering

新框架利用话语结构改进长文档问答

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-08 04:00

研究人员开发了一种新颖的面向话语的层次化框架，用于长文档的问答。该方法利用修辞结构理论（RST）解析话语树，并使用基于LLM的节点嵌入来增强句子级表示。该框架的结构引导式层次化检索方法已在各种数据集、体裁和语言中展示出持续的改进，通过整合话语结构优于现有方法。 AI

影响引入了一种利用话语结构的长文档问答新方法，有望提高对复杂文本的理解和检索准确性。

排序理由这是一篇详细介绍长文档问答新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

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; 这是一篇详细介绍长文档问答新框架的研究论文。[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, 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: 161 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。

arXiv cs.CL TIER_1 English(EN) · Huiyao Chen, Yi Yang, Yinghui Li, Meishan Zhang, Baotian Hu, Min Zhang · 2026-05-08 04:00

超越分块：面向长文档问答的语篇感知分层检索

arXiv:2506.06313v5 Announce Type: replace-cross Abstract: Existing long-document question answering systems typically process texts as flat sequences or use heuristic chunking, which overlook the discourse structures that naturally guide human comprehension. We present a discours…