70How do you measure faithfulness (hallucination rate) in a RAG system, and what makes it hard to score?▼mediumAnthropicCohereDatabricks1 replies◆ premiumAn answer can be correct yet still unfaithful, asserting things the retrieved context never said. The signal is scoring faithfulness against the context, not against truth, and knowing why LLM-judge faithfulness scores drift.Open full answer →
71Context precision versus context recall: which do you optimize, and how do they trade off in RAG?▼mediumCohereGleanDatabricks2 replies◆ premiumPushing top-k higher raises recall but buries the answer in noise, and a tight reranker raises precision but can discard the one chunk you needed. The signal is knowing which metric caps the system and how to move both with a retrieve-wide-then-rerank shape.Open full answer →
