measurement
In the CCM Code Proposal dataset evaluation, the Dense Vector (ada-002) method achieved a 23% winning rate and an average score of 3.48, while the GraphRAG (GPT-4o) method achieved a 77% winning rate and an average score of 4.04.
Authors
Sources
- Efficient Knowledge Graph Construction and Retrieval from ... - arXiv arxiv.org via serper
Referenced by nodes (1)
- GPT-4 concept