AI Engineer: NLP and Large Language Models Flashcards

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

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

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

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

Answer: Perplexity

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

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

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

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

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

Answer: Storing and querying high-dimensional embeddings for semantic similarity search

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

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

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

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

What does 'temperature' control in LLM text generation?

Answer: The randomness of token sampling — higher values produce more diverse outputs

Temperature scales the logits before softmax; higher values flatten the distribution (more random), lower values sharpen it (more deterministic).