Glossary

Large language model (LLM)

An AI model trained to predict text from patterns. It can write fluently on almost any topic - but fluency is not accuracy, so its claims need grounding to be trusted.

A large language model (LLM) is an AI system trained on vast amounts of text to predict what words come next. From that single skill - guessing the most likely continuation - comes its apparent ability to answer questions, summarize documents, translate, and write.

How it works

An LLM learns statistical patterns across billions of sentences. When you give it a prompt, it doesn't look anything up; it generates a response token by token, each choice shaped by the patterns it absorbed during training. There is no database of facts inside it - only a compressed sense of how language tends to flow.

This is why an LLM can be so useful and so unreliable at once. Predicting fluent text is not the same as stating true text. A model will produce a confident, well-formed sentence whether or not the underlying claim is correct, because correctness was never what it optimized for. When that gap shows - a plausible answer with no basis in reality - it's called an AI hallucination.

Why grounding matters

On its own, an LLM answers from memory: a blur of everything it once read, with no way to point at a source. You can't check its work, because there's nothing to check it against.

Grounding closes that gap. Instead of asking the model to recall, you retrieve the relevant passages from a real document and place them in front of it - the approach known as retrieval-augmented generation. The model then writes from text you can see, and source-grounding keeps each statement tied to the passage it came from. The output stops being a guess and becomes something verifiable.

How an LLM "knows" things, versus traditional software

The comparison that makes an LLM click for most people is against the software they already understand - a spreadsheet formula, a search index, a rules engine. Traditional software is deterministic: a developer writes explicit logic, and the same input always produces the same output because a human specified exactly what should happen in every case. An LLM has no such rules written anywhere. What it "knows" is a statistical pattern absorbed from training text, which is why it can handle a question no one explicitly programmed for - and also why it can state something false with the same fluent confidence as something true.

Large language modelTraditional rule-based software
How it "knows" thingsStatistical patterns learned from training textExplicit rules and logic written by a developer
Handles novel/unseen inputYes - generalizes from patterns, often gracefullyNo - only handles cases the rules anticipate
Same input, same outputNot guaranteed (can vary run to run)Always, unless the code or data changes
Can explain why it produced an answerNot directly - no built-in citation to a ruleYes - traceable to the exact rule or line of code
Can be confidently wrongYes - fluency and accuracy are independentNo - wrong output means a bug, not a "guess"
Improves byTraining on more/better dataA developer changing the code

Neither model is strictly better - they're suited to different problems. A tax calculator should be deterministic rule-based software, because "confidently wrong" is unacceptable there. A tool that has to make sense of open-ended human language - a question, a document, a request phrased ten different ways - is exactly the kind of problem an LLM is built for, because no developer could pre-write rules for every possible phrasing.

This is the whole shape of how Sidenote works: it reads your document, retrieves the passages that matter, and grounds every answer in them - so each claim carries a citation you can click straight back to the source. See it in action on the Citations feature page.

Frequently asked questions
A large language model is software trained on huge amounts of text to predict the next word in a sentence. Repeating that one trick, word after word, is enough to produce fluent answers, summaries, and explanations - but it means the model is generating plausible text, not looking up verified facts.
An LLM is one type of AI, not the whole field. Artificial intelligence covers everything from spam filters to self-driving cars; a large language model is specifically a text-prediction system trained on language. Most of what people mean when they say "AI" in 2026 - chatbots, writing assistants, document Q&A - is an LLM at the core, wrapped in extra tooling.
All terms
Ready when you are

Stop digging. Start asking.

Add Sidenote to your browser, open any page in your wiki, and ask it the question you’ve been Slacking the team about.

7-day Pro trial · No card required · Free plan forever