Short answer
Large language models are deep neural networks trained on massive text corpora to predict tokens, enabling chat, coding help, summarization, and tool-using applications.
Why it matters
LLMs are the interface layer of modern AI products. Understanding tokens, context, and grounding strategies prevents costly misuse.
Article
Patterns
Start with RAG + low temperature for factual apps; add fine-tunes when format stability demands it.
Examples
Instruction following in chat
A user asks an LLM to turn meeting notes into action items grouped by owner. The model reformats the text using patterns learned from instruction tuning. A project manager still verifies owners and deadlines before assigning work in a tracker.
Code assistance with tests
A developer asks an LLM to sketch a function and unit tests. The model proposes code based on similar patterns in training data. Running tests and reviewing edge cases remains the reliability gate before merging.
FAQ
What is a token?
A token is a chunk of text used as a modeling unit—often a word piece or character sequence—not always a full word. Models read and generate tokens; pricing and context limits are commonly measured in tokens.
Why do LLMs hallucinate?
LLMs optimize for plausible continuations, not guaranteed truth. When evidence is missing or prompts push beyond reliable knowledge, the model may still produce fluent text. Grounding with retrieval, tools, citations users can open, and human review reduces—but does not magically eliminate—this risk.
Related glossary terms
- AI agent — A system that pursues goals by choosing actions over multiple steps, often using tools, memory, and feedback from an…
- Embedding — A numeric vector representation of an item—such as a token, sentence, image, or document—used to capture similarity and…
- Fine-tuning — Additional training that adapts a pretrained model to a narrower task, domain, or preferred behavior using specialized…
- Generative AI — AI systems that create new content—such as text, images, audio, or code—by modeling patterns from training data.
- Hallucination — When a generative model produces fluent content that is fabricated, unsupported, or inconsistent with provided sources.
- Inference — The process of running a trained model on new inputs to produce predictions or generations, usually without updating…
- Large language model — A large neural network, typically a transformer, trained on massive text corpora to predict tokens and perform language…
- Multimodal — AI systems that process or generate more than one data type—such as text, images, audio, or video—within a unified…
- Natural language processing — The AI subfield focused on analyzing, understanding, and generating human language for tasks like translation, search…
- Prompt — The input text or structured instructions given to a generative model to steer its output toward a desired task or…
- RAG (retrieval-augmented generation) — A pattern that retrieves relevant documents and conditions a generative model on that evidence to improve grounded…
- Token — A chunk of text (often a word piece) used as a basic unit for language model training, context limits, and generation.
- Transformer — A neural network architecture that uses attention mechanisms to model relationships among tokens in a sequence…
Sources
-
CS224N: Natural Language Processing with Deep Learning
Stanford UniversityUniversity course covering word vectors, transformers, and modern NLP systems underlying LLMs.
-
Text generation guide
OpenAIOfficial conceptual documentation for LLM text generation behavior.