English(EN) Explore-on-Graph: Hybrid Embedding-LLM Reasoning for Knowledge Graph Question Answering under Incompleteness

新框架XoG增强了LLM在不完整知识图谱上的问答能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 04:00

研究人员开发了一个名为Explore-on-Graph (XoG)的新框架，旨在改进不完整知识图谱上的问答。XoG通过学习从图结构本身恢复推理路径来解决知识图谱中事实缺失的问题，而不是依赖LLM生成可能产生幻觉的信息。该框架整合了实体关系统计信息和KG嵌入，以识别可能缺失的实体，并使用LLM作为语义选择器。在各种基准测试上的实验表明了XoG的有效性，它在完整图谱上保持竞争力，在面对缺失数据时优于其他方法，同时还减少了LLM的token消耗。 AI

影响这项研究通过提高LLM处理不完整数据能力，有望带来更强大、更高效的基于LLM的问答系统。

排序理由该集群描述了一篇关于知识图谱问答新颖框架的最新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 25 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇关于知识图谱问答新颖框架的最新研究论文。[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, infra; 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.CL TIER_1 English(EN) · Ola El Khatib, Djellel Difallah · 2026-10-01 04:00

Explore-on-Graph：混合嵌入-LLM推理用于不完整知识图谱问答

arXiv:2609.39786v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly combined with knowledge graphs (KGs) to ground reasoning in structured evidence. However, most LLM-based KGQA methods rely on traversing existing graph edges and become unreliable when r…

本文如何被排名

报道来源 [1]

Explore-on-Graph：混合嵌入-LLM推理用于不完整知识图谱问答

相关实体

相关话题