Data Language
ProductsMaturity ModelsBlogNewsAboutContact
Interventions
Intervention

Integrate a Large Language Model (LLM) AI with a Knowledge Graph

Connect a Large Language Model AI service with a knowledge graph so that the information source is scoped and accurate. This provides a reliable information repository for using the LLM in a specific business area.
Solves these Problems
LLM / GPT AI is not trained on complete, accurate information
Knowledge Graph intelligence not accessible to business users
Improves these Problems
Unable to generate realtime actionable intelligence
LLM / GPT AI hallucinates incorrect information
Involves these Technologies
Machine Learning (ML)
Large Language Model (LLM) AI
A large language model (LLM) is a language model consisting of a neural network with many parameters, trained on large quantities of unlabelled text using self-supervised learning.
Retrieval-Augmented Generation (RAG) with LLMs
RAG is an AI technology pattern that employs large language models (LLMs) to retrieve facts from a specific knowledge base.
Knowledge Graphs
Data Language is a market leader in the design, implementation, and deployment of knowledge graphs (KGs), and we have developed a Knowledge Graph as a Service platform that enables exploration and speed-to-market.
Related Articles
Insights from the KCL LLM Knowledge Prompting Hack Event 2023
Insights from the KCL LLM Knowledge Prompting Hack Event 2023
Integrate a Large Language Model (LLM) AI with a Knowledge Graph
From 7th-10th August, we joined Kings College London Informatics Department in their 2023 Knowledge Prompting Hackathon using LLMs and Knowledge Graphs. Here are some early insights.
Anthony Hughes
Anthony Hughes
August 14, 2023
LLM and Knowledge Graph Hack Event with KCL & Turing Institute
LLM and Knowledge Graph Hack Event with KCL & Turing Institute
Integrate a Large Language Model (LLM) AI with a Knowledge Graph
This week, Data Language is joining researchers, practitioners and experts in a Kings College London and Alan Turing Institute hack event focused on LLMs, Generative AI and Knowledge Graph tech.
Matt Shearer
Matt Shearer
August 7, 2023
LLMs, Content Graphs, and The Golden Age for Knowledge Graphs, from KGC2023
LLMs, Content Graphs, and The Golden Age for Knowledge Graphs, from KGC2023
Knowledge Graph Conferences
Our reflections and insights on the themes from KGC2023, including combining LLMs and Knowledge Graphs, and why we are entering a golden age for knowledge graphs.
Matt Shearer
Matt Shearer
June 14, 2023
LLMs and Knowledge Graphs - Data Language Spring 2023 Hack Event
LLMs and Knowledge Graphs - Data Language Spring 2023 Hack Event
Integrate a Large Language Model (LLM) AI with a Knowledge Graph
We held a hack event to explore how we might use LLMs to help with common Knowledge Graph customer use cases.
Matt Shearer
Matt Shearer
April 25, 2023
FAQs
What can you do with an LLM and a knowledge graph?

LLMs can be used to get information into your knowledge graph, and to get intelligence out of your knowledge graph. Some examples are:-

  1. Ask questions about the information in your knowledge graph using natural language queries, both vocal and written.
  2. Generate natural language reports using information in your knowledge graph.
  3. Generate visual reports using information in your knowledge graph.
  4. Create structured data to feed into your knowledge graph from unstructured sources; websites, videos, books, archives etc.
  5. Fill in missing information in your knowledge graph; e.g. summaries, data.
What are the main problems when integrating LLMs with knowledge graphs?
  1. Hallucinations: The LLM creates fictitious data/information that looks convincing, but is in fact nonsense. This includes e.g. wikidata IDs and IAB IDs for datasets that it might claim to know.
  2. Control: Getting the LLMs to "stay on the rails" and do what you ask - e.g. sticking to constraints that you feed into the process.
  3. Repeatability: Getting reliable and consistent results back is currently an issue.

These FAQ answers are based on tests in summer 2023 on chatGPT and Bard. They should all improve during 2023-2024. We are keeping track of feature areas.

What are the benefits of using LLMs with Knowledge Graphs?
  1. An LLM can be used as a natural language interface onto your knowledge graph.
  2. A knowledge graph provides an information source with context and meaning to an LLM service.
  3. A knowledge graph can scope the information used by the LLM to your business area, so that you are not plagued with hallucinations from elsewhere in an LLMs training corpus.
  4. Some LLMs understand RDF models, SPARQL and Cypher graph querying languages, so they can make full use of your graph structure.