Skip to content
Hot eventLive

NavTree:无需LLM摘要的层级检索长文档问答研究

1 reports1 sources3 hr ago updated

Get the story

AI overview

2026年10月7日,arXiv Computation and Language(一手)报道一项长文档问答的层级检索研究,提出 NavTree。该方法仅在叶节点输出,索引阶段零 LLM 调用,构建确定性平衡分段树;查询时以混合词频与稠密前沿游走,从根节点导航到叶块。评测显示,在匹配成本评测中,NavTree 是最强的匹配成本层级检索器,与最强扁平基线持平;在长文档多跳 QA 中,它是唯一在类对类基础上显著超过 BM25 的层级方法。目前报道未涉及后续更新或争议。

Generated from reports · updated 3 hr ago

Timeline

Follow the coverage from different angles.

Oct 7, 2026
  1. arXiv · Computation and Language
    长文档问答的层级检索研究:无需 LLM 摘要的树导航

    研究提出 NavTree,一种仅在叶节点输出的层级检索器:索引阶段零 LLM 调用,构建确定性平衡分段树,查询时以混合词频与稠密前沿游走从根节点导航到叶块。在匹配成本评测中,NavTree 是最强的匹配成本层级检索器,与最强扁平基线持平;在长文档多跳 QA 中,它是唯一在类对类基础上显著超过 BM25 的层级方法。

Heat trend

Current heat 9·Comparable peak 10(Oct 7)·Comparable change over 24 hours –

02.557.510Oct7Oct7Oct7Oct7

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.