AB-731: AI Transformation LeaderDemo

Question

For each of the following statements about Retrieval Augmented Generation (RAG), select Yes if the statement is true. Otherwise, select No.

Yes or No

Statements	Yes	No
Retrieval Augmented Generation (RAG) architectures require that a large language model (LLM) be retrained on proprietary data.
Retrieval-Augmented Generation (RAG) grounds a language model to produce more factual and context-relevant responses.
Retrieval Augmented Generation (RAG) retrieves information from external knowledge sources at runtime instead of relying solely on the knowledge of a generative AI model.

Explanation

RAG works by retrieving relevant documents or data from an external knowledge base (such as a vector store) at inference time and injecting that context into the prompt sent to the LLM. This means the base model itself does not need to be retrained or fine-tuned on the proprietary data - the knowledge is supplied dynamically through retrieval, making the first statement false. Because the retrieved content provides up-to-date, domain-specific, and factual context, RAG grounds the model's responses, reducing hallucinations and improving relevance and accuracy, making the second statement true. Finally, RAG's defining characteristic is that it augments generation by pulling information from external sources at runtime rather than depending solely on the parametric knowledge baked into the model during pretraining, making the third statement true.

Learn more

Retrieval Augmented Generation (RAG) in Azure AI Search

AB-731: AI Transformation LeaderDemo

AstroTutor

Notes

Readiness

QuestionQ12

Community Discussion