English(EN) STEM: Structure-Tracing Evidence Mining for Knowledge Graphs-Driven Retrieval-Augmented Generation

STEM框架通过结构追踪证据挖掘增强知识图谱推理

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-24 06:56

研究人员推出STEM，一个旨在增强基于知识图谱的问答的新框架。该方法解决了知识图谱的结构异质性以及现有推理路径检索方法缺乏全局视角的问题。STEM将多跳推理重构为模式引导的图搜索，提高了检索任务的准确性和证据完整性。 AI

影响提高了知识图谱问答中多跳推理的准确性和证据完整性。

排序理由介绍新知识图谱推理框架的学术论文。

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) · Peng Yu, En Xu, Bin Chen, Haibiao Chen, Yinfei Xu · 2026-04-27 04:00

STEM：面向知识图谱驱动的检索增强生成的结构追踪证据挖掘

arXiv:2604.22282v1 Announce Type: new Abstract: Knowledge Graph-based Question Answering (KGQA) plays a pivotal role in complex reasoning tasks but remains constrained by two persistent challenges: the structural heterogeneity of Knowledge Graphs(KGs) often leads to semantic mism…
arXiv cs.CL TIER_1 English(EN) · Yinfei Xu · 2026-04-24 06:56

STEM：面向知识图谱驱动的检索增强生成结构追踪证据挖掘

Knowledge Graph-based Question Answering (KGQA) plays a pivotal role in complex reasoning tasks but remains constrained by two persistent challenges: the structural heterogeneity of Knowledge Graphs(KGs) often leads to semantic mismatch during retrieval, while existing reasoning …