If your retriever returns 5 documents but only 1 was actually related to answering the question, how do you penalize the retriever for the "noise"?

What is the difference between testing your model on a static CSV file (Offline) vs. monitoring real user "Thumbs Up/Down" feedback (Online)?

If you are using an LLM to grade another LLM, why is it critical to provide a "multi-point rubric" rather than just asking "Is this answer good?"

What is a "Golden Dataset" (or Ground Truth set), and how many samples should it ideally contain before you can trust your evaluation metrics?