The experimental evaluation of the LLM agent framework utilized OpenAI’s GPT-4o via Langchain QA chains, interacting with a Neo4j knowledge graph through LLM-generated Cypher queries, with configuration settings of temperature 0.0, top_p 0.95, and a 4096-token limit.

Authors

• Person: Not available Organization: arXiv
  Leveraging Knowledge Graphs and LLM Reasoning to Identify ...

Sources

• Leveraging Knowledge Graphs and LLM Reasoning to Identify ... arxiv.org arXiv via serper

Referenced by nodes (5)

• Knowledge Graph concept
• GPT-4 concept
• OpenAI entity
• Neo4j entity
• Cypher concept