Exams / AIF-C01 / Generative AI concepts / Question 2
AIF-C01 practice question: Generative AI concepts (2 of 5)
Fundamentals of Generative AI A free question from our original AIF-C01 practice exam. Try it, then open the answer to see why each option is right or wrong.
A recruitment site wants a search feature that finds CVs with similar meaning to a job description, even when they use different words. Which concept makes this possible?
Choose one answer.
- AA. Embeddings, which represent meaning as vectors of numbers
- BB. Stop sequences, which tell the model when to stop generating text
- CC. Temperature, which controls how random the generated text is
- DD. Tokens, which split text into the words the site already indexes
Show the answer and explanation
Answer: A
- A. Right: Correct. Embeddings are numerical vectors that represent meaning, so similar texts end up near each other and can be compared.
- B. Wrong: Stop sequences control where generation ends. They play no part in comparing the meaning of two documents.
- C. Wrong: Temperature affects the randomness of generated output, not how documents are matched by meaning.
- D. Wrong: Tokenising alone gives word pieces. Matching on those would still miss CVs that use different words.
Explanation
An embedding model converts text (or images) into a vector of numbers that captures its meaning. Texts with similar meaning have vectors that are close together, so a vector search can find relevant matches even without shared keywords. This is the basis of semantic search and RAG.
Study
Keep practising
Answer questions with a score at the end, or practise just this topic with the explanation after each one. No sign-up needed.