Knowledge Tree
Relations (1)
related 2.81 — strongly supporting 6 facts
Knowledge graphs and semantic similarity are linked through methodologies that quantify relationships between concepts [1] and the use of vector embeddings to compare data points [2]. Furthermore, research specifically addresses the computation of semantic similarity within the structure of knowledge graphs {fact:2, fact:6}, contrasting this approach with the vector-based similarity searches used in RAG systems [3].
Facts (6)
Sources
Applying Large Language Models in Knowledge Graph-based ... arxiv.org 3 facts
claimSemantic similarity in knowledge graphs is developed by introducing quantitative values to the relationship between two concepts.
referenceZhu, G. and Iglesias, C.A. published the paper 'Computing semantic similarity of concepts in knowledge graphs' in the IEEE Transactions on Knowledge and Data Engineering in 2016.
claimLLM-based and KG-based approaches use knowledge graphs as input, but LLM-based approaches shift the processing methodology away from semantic similarity measures toward using LLMs to assess domain concept instantiation within a modeling language.
Combining Knowledge Graphs With LLMs | Complete Guide - Atlan atlan.com 1 fact
claimVector embeddings capture semantic similarity between data points but fail to capture explicit relationships between entities, whereas knowledge graphs provide structured connections that vector search cannot infer.
Knowledge Graphs: Opportunities and Challenges - Springer Nature link.springer.com 1 fact
claimZhu and Iglesias (2018) proposed the SCSNED method for entity disambiguation, which measures semantic similarity based on both informative words of entities in knowledge graphs and contextual information found in short texts.
Knowledge Graphs vs RAG: When to Use Each for AI in 2026 - Atlan atlan.com 1 fact
claimKnowledge graphs utilize graph traversal following explicit relationships for retrieval, while RAG systems utilize semantic similarity search across vector space.