To fact-check the LLM, the authors use the Cypher query language to return relevant coverage nodes and their descriptions from the knowledge graph, then perform a similarity match between the LLM response and the retrieved knowledge graph information using embeddings.

Authors

• Person: Not available Organization: LinkedIn
  Enhancing LLMs with Knowledge Graphs: A Case Study - LinkedIn

Sources

• Enhancing LLMs with Knowledge Graphs: A Case Study - LinkedIn www.linkedin.com LinkedIn via serper

Referenced by nodes (3)

• Knowledge Graph concept
• embeddings concept
• Cypher concept