English(EN) LLM-Based Knowledge Graph Completion Combining Discrete Structural Coding with Similar Entity Information

新的CoSC方法增强了基于LLM的知识图谱补全

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-01 04:00

研究人员开发了一种名为CoSC的新方法，用于基于大型语言模型（LLM）的知识图谱补全（KGC）。CoSC整合了离散结构编码与相似实体信息，以提高排名准确性。在FB15k-237数据集上的实验表明，CoSC在平均倒数排名（MRR）和Hits@10指标上优于现有基线，同时在Hits@1上保持了竞争力。 AI

影响这项研究可以提高知识图谱补全任务的准确性和效率，使依赖结构化知识的AI系统受益。

排序理由该集群包含一篇详细介绍知识图谱补全新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

FB15k-237

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: 23 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍知识图谱补全新方法的论文。[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, other; 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.AI TIER_1 English(EN) · Jiaqi Wang, Dongying Lin, Yang Yang, Yinan Liu, Bin Wang, Xiaochun Yang · 2026-09-01 04:00

结合离散结构编码与相似实体信息的基于LLM的知识图谱补全

arXiv:2608.30235v1 Announce Type: new Abstract: Knowledge graph completion requires models to use both textual descriptions and relational structure. Existing LLM-based methods either encode KG structure as discrete tokens or refine a restricted set of candidate entities, and the…

本文如何被排名

报道来源 [1]

结合离散结构编码与相似实体信息的基于LLM的知识图谱补全

相关实体

相关话题