🎙 Free live masterclass · Sun, 29 Nov, 7:00 pm IST · Java Full Stack roadmap Register free →
Skills101
← All topics

Quiz: Evaluating LLM Apps: questions with answers

10 questions, each with the answer and a short explanation.

Take the timed quiz + get a certificate →
  1. Q1. Why isn't trying a few questions by hand enough?
  2. Q2. Which cases belong in a good test set?
  3. Q3. What should you do before trusting an LLM-as-judge?
  4. Q4. You change the prompt and the model at the same time and the score drops. What's the problem?
  5. Q5. In the harness above, what was the most useful output?
  6. Q6. What does this print? (code)
  7. Q7. Which scoring method fits "the answer must be valid JSON and under 80 words"?
  8. Q8. Why does the lesson prefer yes/no rubric checks over 1–10 scores for an LLM judge?
  9. Q9. A bug reaches production. What should happen to the test set?
  10. Q10. The provider releases a new model version. What should you do before switching?