1/3
These flashcards cover key vocabulary and concepts related to LLM mechanics in AI.
Name | Mastery | Learn | Test | Matching | Spaced | Call with Kai |
|---|
No study sessions yet.
What is Retrieval-Augmented Generation (RAG)?
A system that retrieves external documents before generating responses.
How does RAG reduce hallucinations?
By constraining generation to retrieved, verified information.
Why might an AI struggle with a long legal document?
Due to context window limits, token loss, and diluted attention.
Why should LLMs not be blindly trusted for high-stakes reasoning?
Because they are probability engines, not truth engines.