LLM (large language model)

DefinitionA large language model is an AI model trained on very large amounts of text to predict and generate language. GPT, Claude and Gemini are LLM families.

On its own, an LLM answers from what it learned in training, which stops at a cutoff date and carries no links. Assistants like ChatGPT, Claude, Gemini and Perplexity add web search on top, so the model can read fresh pages and cite them. That retrieval step is where AEO and GEO work has most effect.

Learn it step by step

• How AI engines pick the sources they cite (AEO and GEO fundamentals)

Related terms

• Retrieval-augmented generation (RAG): Retrieval-augmented generation is a method where an AI model first retrieves relevant documents, then writes its answer using them, often citing them as sources.
• Query fan-out: Query fan-out is when an AI search system turns one question into several narrower searches, retrieves results for each and combines them into one answer.
• AI crawler: An AI crawler is a bot run by an AI company that fetches web pages, for model training, for an AI search index, or because a user asked the assistant to read a page.