LLM (Large Language Model)
Definition
A large language model (LLM) is a deep-learning model trained on billions of text tokens to predict and generate human-readable language. LLMs such as GPT-4, Claude, and Gemini power chatbots, document summarization, code generation, and AI workflow automation -- and serve as the reasoning engine inside RAG systems and AI agents.
LLMs learn statistical patterns across massive text corpora, developing emergent capabilities including reasoning, translation, summarization, and code generation. The largest models have hundreds of billions of parameters and are trained on multi-month GPU cluster runs costing tens of millions of dollars.
Key LLM concepts for buyers
- Context window -- how much text the model can process at once (4K to 1M+ tokens)
- Temperature -- controls randomness; lower values give more deterministic outputs
- System prompt -- instructions that shape the model''s behavior for your use case
- Hallucination -- the model confidently generates false information; mitigated by RAG and grounding
Choosing an LLM for your project
Most enterprise AI implementations use API-hosted LLMs (OpenAI, Anthropic, Google) rather than self-hosted models. Self-hosting is warranted when data cannot leave your network -- typically a GovCon or HIPAA requirement.
Related terms
RAG (Retrieval-Augmented Generation)
Retrieval-augmented generation (RAG) is an AI architecture that supplements a large language model's static training knowledge with real-time retrieval from a private or external knowledge base. RAG reduces hallucinations by grounding LLM responses in verified source documents, making it the standard pattern for enterprise AI assistants built on proprietary data.
AI Agent
An AI agent is an LLM-powered system that autonomously plans, selects tools, executes multi-step tasks, and loops until a goal is achieved -- without requiring step-by-step human instruction. AI agents extend a language model''s capability from answering questions to taking actions: writing code, querying APIs, browsing the web, and updating databases.
Prompt Engineering
Prompt engineering is the practice of designing, testing, and iterating on the instructions given to a large language model to reliably produce accurate, consistent, and useful outputs. Well-engineered prompts can increase LLM task accuracy by 20-50% compared to naive instructions, often eliminating the need for more expensive fine-tuning.
Hallucination
Hallucination is the failure mode where a large language model generates plausible-sounding but factually incorrect information with apparent confidence. Studies show unmitigated LLMs hallucinate on 15-30% of factual queries, making hallucination mitigation a mandatory engineering requirement -- not a nice-to-have -- for any production AI system that surfaces facts.
Need help implementing this in your business?
Code and Trust translates AI concepts like llm (large language model) into working implementations — starting with a workflow audit that shows exactly where it creates ROI.
Schedule AI Audit →