Skip to content
Hot eventLive

FoG:前瞻感知证据检索框架用于KBQA

1 reports1 sources3 hr ago updated

Get the story

AI overview

2026年10月7日,arXiv(Computation and Language,一手)发表论文,提出 Foresight-over-Graph(FoG),一个面向知识库问答的前瞻感知证据检索框架。该框架用远到近反馈引导路径探索,并维护紧凑记忆子图。论文称在常用 KBQA 基准上取得 SOTA,其中 CWQ 的 Hit 提升 16.58%,同时减少 LLM 调用与 token 用量;代码已开源。目前公开信息仅此一篇报道,尚无后续验证或第三方复现结果。

Generated from reports · updated 3 hr ago

Timeline

Follow the coverage from different angles.

Oct 7, 2026
  1. arXiv · Computation and Language
    Foresight-over-Graph:知识库问答中超越局部视野的推理

    论文提出 Foresight-over-Graph(FoG),一个面向知识库问答的前瞻感知证据检索框架,用远到近反馈引导路径探索并维护紧凑记忆子图。在常用 KBQA 基准上取得 SOTA,CWQ 的 Hit 提升 16.58%,同时减少 LLM 调用与 token 用量;代码已开源。

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.