AI AI Engineer: NLP and Large Language Models 3

Question 1

What is 'vector similarity search' used for in LLM-powered applications?

Accepted Answer

Finding the most semantically similar documents to a query by comparing embedding vectors

Answer

Vector similarity search retrieves documents whose embeddings are closest to a query embedding, powering RAG, semantic search, and recommendation systems.

Question 2

Which metric measures how well an LLM predicts a test corpus, with lower values indicating better language modeling?

Accepted Answer

Perplexity

Answer

Perplexity measures the exponentiated average negative log-likelihood of a test set; lower perplexity means the model assigns higher probability to the observed text.

Question 3

What is 'chain-of-thought prompting' in LLMs?

Accepted Answer

Prompting the model to reason through intermediate steps before giving a final answer

Answer

Chain-of-thought prompting encourages LLMs to explicitly generate reasoning steps, significantly improving performance on complex reasoning tasks.

Question 4

What is a vector database's primary role in an LLM application architecture?

Accepted Answer

Storing and querying high-dimensional embeddings for semantic similarity search

Answer

Vector databases (e.g., Pinecone, Weaviate, Chroma) store embeddings and support fast approximate nearest-neighbor search for retrieval in RAG pipelines.

Question 5

What is 'semantic chunking' in the context of building RAG systems?

Accepted Answer

Dividing documents into chunks based on semantic coherence to preserve meaningful context

Answer

Semantic chunking splits documents at natural semantic boundaries rather than fixed sizes, improving retrieval quality by keeping coherent content together.

AI - Engineer Practice Test

AI - Engineer Practice Test

AI AI Engineer: NLP and Large Language Models 3