Retrieval-augmented generation (RAG)
Giving a language model relevant documents at the time of the question, so answers are grounded in them.
The system searches an approved knowledge source, often a vector database of embeddings, and passes the retrieved text to the model with the question. It reduces hallucination and keeps answers current without retraining, but depends on the quality and access controls of the source content.
On the exam
Audit the knowledge base: is it accurate, current and access-controlled? Users mustn’t retrieve documents they aren’t entitled to see.
Related terms
- Large language model (LLM)A generative model trained on huge amounts of text to understand and produce language.
- HallucinationConfident but false output from a generative AI model.
- Fine-tuningFurther training a pre-trained model on specific data to adapt it.
AAIA Test yourself on this with timed AAIA practice questions in the AAIA Exam Simulation Hub, or read the free AAIA exam guide.
Test yourself with today’s question of the day.
