LLM (Large Language Model) is a type of AI model trained on vast amounts of text data to generate human-like responses to natural-language prompts. LLMs power the AI search platforms where brand visibility is measured — ChatGPT, Perplexity, Gemini, Claude, and Grok.Documentation Index
Fetch the complete documentation index at: https://docs.getcited.in/llms.txt
Use this file to discover all available pages before exploring further.
Why it matters
LLMs are the “search engines” of AI search. Understanding how they generate responses — blending training data with optional live retrieval, exhibiting non-determinism, and preferring certain source types — is a prerequisite for effective GEO work. Each LLM has different behavior: ChatGPT uses Bing for retrieval, Perplexity always searches live, Claude relies more on training data.How Cited uses it
Cited tracks five LLMs via their APIs, each queried with the same set of consumer-authentic prompts. The specific model versions and costs are documented in Which LLMs we track. Each LLM contributes independently to a brand’s overall visibility score.Related concepts
- Which LLMs we track — the specific models and rationale
- Non-determinism — a fundamental property of LLMs
- RAG — how some LLMs augment training data with live retrieval