Faithfulness measures whether an answer accurately reflects the provided context without adding unsupported claims. Hallucination is the failure mode where the model fabricates, contradicts, or overextends beyond the evidence.
Faithfulness is not the same as correctness. An answer can be faithful to bad context and still be wrong. That is why RAG evals often pair faithfulness with retrieval quality and answer correctness.
A faithful answer can still be incomplete or irrelevant. Faithfulness should be evaluated alongside correctness, relevance, coverage, and retrieval quality.