Large language model (LLM)
A generative model trained on huge amounts of text to understand and produce language.
LLMs predict the next piece of text based on patterns learned in training. They can summarise, draft, translate and answer questions, but don’t “know” facts and can produce confident errors. Outputs can vary between runs.
On the exam
Treat LLM output as a draft to verify, not as evidence. Because outputs aren’t always reproducible, document prompts, versions and settings when outputs matter.
Related terms
- Generative AIAI that creates new content: text, images, code or audio.
- Foundation modelA large general-purpose model that can be adapted to many tasks.
- HallucinationConfident but false output from a generative AI model.
- Retrieval-augmented generation (RAG)Giving a language model relevant documents at the time of the question, so answers are grounded in them.
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.
