Glossary

Knowledge cutoff — Glossary

The point in time after which a model’s frozen training data no longer covers world events.

Reviewed:

Full definition

LLMs without browsing or retrieval cannot reliably know facts after their training cutoff. Product UIs should set expectations and use RAG or tools for changing information.

Related encyclopedia topic

Large Language Models — Large language models (LLMs) are neural networks trained on vast text corpora to predict tokens in context, enabling fluent generation, summarization…

← Back to glossary · Learning hub