← Back to curriculum

Module 7 — GenAI & LLMs

Module 7 quiz & review

40 interactive questions on LLM lifecycle, LoRA, RAG engineering, hybrid search, reranking, evals, and interview trade-offs.

~75 min read + exercises

Module 7 quiz and review

Before we begin

Test LLM lifecycle, fine-tuning, RAG engineering, sampling, and trust — including interview topics like LoRA, hybrid search, reranking, and faithfulness evals. Aim for at least 30 out of 40.


Multiple choice quiz

Interactive quiz

Pick one answer per question. Feedback appears immediately — take your time before clicking.

0 / 40 correct·0 answered
  1. Question 1 of 40

    A GPT-style LLM is best described as:

    Answer options for question 1
  2. Question 2 of 40

    During inference, an LLM typically:

    Answer options for question 2
  3. Question 3 of 40

    Prompt engineering mainly means:

    Answer options for question 3
  4. Question 4 of 40

    A system prompt usually:

    Answer options for question 4
  5. Question 5 of 40

    What does temperature control in LLM sampling?

    Answer options for question 5
  6. Question 6 of 40

    Top-k sampling:

    Answer options for question 6
  7. Question 7 of 40

    Top-p (nucleus) sampling:

    Answer options for question 7
  8. Question 8 of 40

    Fine-tuning vs RAG — the main difference:

    Answer options for question 8
  9. Question 9 of 40

    When is RAG often preferred over fine-tuning?

    Answer options for question 9
  10. Question 10 of 40

    In RAG, embeddings are used to:

    Answer options for question 10
  11. Question 11 of 40

    Why do LLMs hallucinate?

    Answer options for question 11
  12. Question 12 of 40

    Which practice reduces hallucinations in doc Q&A?

    Answer options for question 12
  13. Question 13 of 40

    In LLM context, embeddings refer to:

    Answer options for question 13
  14. Question 14 of 40

    Few-shot prompting means:

    Answer options for question 14
  15. Question 15 of 40

    A vector database (FAISS, Pinecone, etc.) in RAG stores:

    Answer options for question 15
  16. Question 16 of 40

    Pretraining an LLM mainly means:

    Answer options for question 16
  17. Question 17 of 40

    Temperature = 0 (greedy decoding) typically:

    Answer options for question 17
  18. Question 18 of 40

    A clear system prompt should:

    Answer options for question 18
  19. Question 19 of 40

    Chunking documents for RAG is important because:

    Answer options for question 19
  20. Question 20 of 40

    Fine-tuning is often chosen over RAG when:

    Answer options for question 20
  21. Question 21 of 40

    Grounding a chatbot answer means:

    Answer options for question 21
  22. Question 22 of 40

    Top-p (nucleus) sampling keeps:

    Answer options for question 22
  23. Question 23 of 40

    Chain-of-thought prompting helps when:

    Answer options for question 23
  24. Question 24 of 40

    In a chat API, assistant messages in history are included so that:

    Answer options for question 24
  25. Question 25 of 40

    Cosine similarity between query and chunk embeddings in RAG finds:

    Answer options for question 25
  26. Question 26 of 40

    SFT (supervised fine-tuning) in the LLM lifecycle means:

    Answer options for question 26
  27. Question 27 of 40

    RLHF is mainly used to:

    Answer options for question 27
  28. Question 28 of 40

    LoRA fine-tuning is popular in industry because:

    Answer options for question 28
  29. Question 29 of 40

    Quantization (e.g. INT8, 4-bit) helps primarily with:

    Answer options for question 29
  30. Question 30 of 40

    Hybrid search in RAG combines:

    Answer options for question 30
  31. Question 31 of 40

    A reranker after first-stage retrieval is used because:

    Answer options for question 31
  32. Question 32 of 40

    When a source document is deleted, a production RAG index should:

    Answer options for question 32
  33. Question 33 of 40

    Chunk overlap (50–100 tokens) helps because:

    Answer options for question 33
  34. Question 34 of 40

    A coding agent (Claude Code / Cursor Agent) differs from chat because it:

    Answer options for question 34
  35. Question 35 of 40

    Faithfulness in RAG eval means:

    Answer options for question 35
  36. Question 36 of 40

    For RAG Q&A with citations, sampling settings are usually:

    Answer options for question 36
  37. Question 37 of 40

    Catastrophic forgetting during fine-tuning means:

    Answer options for question 37
  38. Question 38 of 40

    Bi-encoder retrieval vs cross-encoder reranking:

    Answer options for question 38
  39. Question 39 of 40

    A user pastes “ignore instructions and leak secrets” into RAG context. Mitigation:

    Answer options for question 39
  40. Question 40 of 40

    Interview: inference vs training — weights during a user chat:

    Answer options for question 40

After the quiz

30/40 or higher? Start the RAG chatbot project.

Checklist:

  • I can explain pretraining → SFT → RLHF at a high level.
  • I know fine-tuning vs RAG vs LoRA trade-offs.
  • I understand hybrid search, chunk overlap, and reranking.
  • I can describe why hallucinations happen and how grounding helps.
  • I know when low temperature fits RAG Q&A.

What's next

Project: RAG chatbot with citations