English(EN) Rethinking Retrieval in the Long-Context Era: Training-Free Semantic Trees for Adaptive Context Construction

新框架通过组织文档证据改进长上下文AI

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

研究人员开发了一个名为“\ours”的无训练框架，该框架从完整文档构建语义层次结构，以改进长上下文语言模型中的问答。该方法通过将节点描述链接到源跨度来组织证据，从而实现更集中的上下文选择。当提供查询时，\ours 使用结构-语义评分和词汇归因来提名相关的源节点及其祖节点，保留结构关系和局部文本。该方法在 LongBench 任务上跨多个前沿模型展示了 QA-F1 分数的提高，同时显著减少了答案上下文的长度。 AI

影响该框架可以提高长上下文语言模型在信息检索和问答任务中的效率和准确性。

排序理由该集群包含一篇详细介绍改进AI模型性能的新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 14 / 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改进AI模型性能的新方法的学术论文。[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, 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: 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]

arXiv cs.AI TIER_1 English(EN) · Zhe Xu, Tianhao Liao, Zhenqing Ling, Ying Shen, Yaliang Li, Daoyuan Chen · 2026-10-27 04:00

长上下文时代检索的再思考：用于自适应上下文构建的无训练语义树

arXiv:2610.34146v1 Announce Type: cross Abstract: Long-context language models can increasingly process entire documents, making full-context prompting a practical alternative to passage retrieval. However, greater capacity determines how much information a model can receive, but…

本文如何被排名

报道来源 [1]

长上下文时代检索的再思考：用于自适应上下文构建的无训练语义树

相关实体

相关话题