arXiv cs.CL· Elwin Huaman·· 12 小时前AI 评分20
LLM 时代的知识图谱质量评估：一个概念框架
Knowledge Graphs Quality Assessment in the Era of LLMs: A Conceptual Framework
AI 导读
研究者将现有数据、信息、关联数据与知识图谱质量评估框架扩展为包含 24 个质量维度和多种质量指标的目录，并提出一个通用、可按领域或任务定制、面向实践的 KG 质量评估框架。该工作回应了 LLM 日益依赖 KG 提供简洁、完整、准确、忠实、新鲜且可追溯答案时"KG 质量如何、何时可信、如何评估"的问题。
正文 · 原文
Abstract:Knowledge Graphs (KGs) have been popularized during the last few decades and are increasingly constructed and consumed by Large Language Models (LLMs). Various applications therefore rely on KGs to provide concise, complete, accurate, faithful, fresh, and traceable answers. However, what is the quality of those KGs? In which cases should a KG be used, and can it be trusted to ground an LLM? How might it be evaluated? We reviewed the literature on quality assessment (QA) of data, information, linked data, KGs, and the intersection of KGs and LLMs. We extended the current state-of-the-art frameworks to a catalog of 24 quality dimensions (QDs) and various quality metrics (QMs). Furthermore, we propose a general-purpose, customizable to a domain or task, and practical QA framework for assessing the quality of KGs.
| Comments: | 8 pages, 1 figure, KGSWC 2026 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.31684 [cs.CL] |
| (or arXiv:2610.31684v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31684 arXiv-issued DOI via DataCite |
Submission history
From: Elwin Huaman [view email]
[v1]
Sat, 3 Oct 2026 19:41:14 UTC (1,808 KB)
来源：arXiv cs.CL · arxiv.org