Skip to course content
Free RAG fundamentals course

Introduction to RAG and Knowledge Assistants

Module 04 Knowledge Check

5 questions. Pass mark 4 out of 5. Answer every question before checking the answer key below, then retry after reading the feedback.

1. Why rewrite a user's query before retrieval?

2. In a multi-turn chat, the biggest retrieval failure is usually…

3. The right first diagnostic when answers are poor is…

4. Splitting a complex question into sub-queries helps because…

5. A risk of automatic query rewriting is…

---

Answer Key and Explanations

Check these only after attempting every question.

1. B - Conversational or vague wording often retrieves poorly; an explicit query matches better

"What about the other one?" carries meaning only in conversation. Retrieval needs a self-contained query.

2. B - Pronouns and follow-ups that lose the referent when sent to retrieval alone

Follow-up turns must be resolved against the conversation before they can retrieve anything sensible.

3. B - Inspect what was actually retrieved for that question

Looking at retrieved chunks separates a retrieval problem from a generation problem in seconds.

4. B - Different parts of the answer may live in different documents

A single embedding of a compound question often matches nothing well.

5. B - The rewrite can change the user's meaning, so the system answers a different question confidently

Rewriting is itself a model step and can introduce error. Log the rewritten query so it is inspectable.

Practical Check

Apply this module to your own work: complete the module activity for *Query Rewriting and Retrieval Quality*, then write one sentence naming what your result shows and one naming what it does not.

Strong Answer Pattern

A strong answer names the task, the evidence used, the check performed, and the remaining limitation. It avoids "proved", "guaranteed", or "always" unless the evidence genuinely supports it.