Large Language Models and Knowledge Graphs: Opportunities and Challenges
Большие языковые модели и графы знаний: возможности и вызовы
2023-06-26
SCID: 54.1/a4s2vybd
Discuss with AI
explicit knowledgeknowledge graphsknowledge representationlarge language modelsparametric knowledge
Figures from the paper
Abstract (AI)
Large Language Models (LLMs) have taken Knowledge Representation - and the world - by storm. This inflection point marks a shift from explicit knowledge representation to a renewed focus on the hybrid representation of both explicit knowledge and parametric knowledge. In this position paper, we will discuss some of the common debate points within the community on LLMs (parametric knowledge) and Knowledge Graphs (explicit knowledge) and speculate on opportunities and visions that the renewed focus brings, as well as related research topics and challenges.
Key Findings
1
It identifies a shift in knowledge representation from primarily explicit structures toward combining explicit knowledge with knowledge encoded in model parameters.
2
It presents research opportunities and future visions for integrating LLMs with knowledge graphs, while highlighting related open research challenges.
3
The paper characterizes LLMs as parametric knowledge stores and knowledge graphs as explicit knowledge representations within a hybrid representation paradigm.
4
The paper synthesizes community debates concerning the complementary roles, opportunities, and challenges of LLMs and knowledge graphs.
Research Object
Large Language Models and Knowledge Graphs as hybrid representations of parametric and explicit knowledge
Research Subject
Opportunities, visions, debate points, research topics, and challenges in integrating parametric knowledge from LLMs with explicit knowledge from Knowledge Graphs
Publication Details
Publication Date
2023-06-26
Journal
Publisher
ISSN
Cited by
84
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest