AI engineering glossary · RAG vector search
What is faithfulness?
Faithfulness: A RAG evaluation measure of whether every claim in the answer is supported by the retrieved context. It is usually computed as supported claims divided by total claims, and detects made-up content even when the answer sounds plausible.
Faithfulness: an example
If 8 of 10 claims in an answer are supported by the context, faithfulness = 8 / 10 = 0.8.
Related terms
More RAG vector search terms
- Fixed-size chunking
- Flat index
- Full-text search
- Golden dataset
- GraphRAG
- Hallucination
- Hamming distance
- Hierarchical chunking
Where you learn it
Faithfulness is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.