/4 min/reference
Separating Retrieval Failures From Generation Failures in RAG Evaluation
Score retrieval and generation separately: the pair of metrics localizes whether a bad RAG answer is a retriever or an LLM problem.
Tag
2 posts.
Score retrieval and generation separately: the pair of metrics localizes whether a bad RAG answer is a retriever or an LLM problem.
Mine failing production traces, store input plus retrieved chunks plus expected behavior, and version 50-100 focused cases in-repo.