English(EN) GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases

GRASP框架推进SKB检索，在STaRK基准测试上提高准确性

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-28 17:07

研究人员推出GRASP，一个用于从半结构化知识库（SKBs）中检索信息的新型三阶段框架。该系统集成了基于规划的图检索、密集检索器和重排序器，显著提高了检索准确性。GRASP在STaRK基准测试上取得了重大进展，平均Hit@1得分从62.0提高到73.9。 AI

排序理由该聚类包含一篇详细介绍新检索框架及其基准性能的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CL TIER_1 English(EN) · Yicheng Tao, Yiqun Wang, Xiangchen Song, Xin Luo, Kai Liu, Jie Liu · 2026-05-29 04:00

GRASP：在半结构化知识库上进行基于计划引导的图检索，并采用自适应融合和重排序

arXiv:2605.30237v1 Announce Type: cross Abstract: Semi-structured knowledge bases (SKBs) embed textual documents in a typed graph of entities and relations, and underpin applications such as product search, academic paper search, and precision-medicine inquiries. Existing hybrid …
arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Jie Liu · 2026-05-28 17:07

GRASP：在半结构化知识库上进行基于规划的图检索，并采用自适应融合和重排序

Semi-structured knowledge bases (SKBs) embed textual documents in a typed graph of entities and relations, and underpin applications such as product search, academic paper search, and precision-medicine inquiries. Existing hybrid retrieval systems on SKBs either use the graph onl…