Skip to content

Generative AI & LLMs

TF-IDF

Term frequency–inverse document frequency

A way to highlight words that appear often in one document but less often across other documents.

Example

A search system gives a distinctive technical word more weight than a common word.

Why people use it

It helps a search tool give distinctive words more attention than very common ones.

What you'll hear

“That unusual term should matter more in this document.”

What this means for you

Use it as a transparent text signal with known limitations.

Can you control it?

Developer-only

The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.

Common questions

Does TF-IDF capture every semantic relationship?
No. It counts word patterns rather than fully understanding what the writing means.
Can a word's weight change when the collection changes?
Yes. A word that was rare may become common as more documents are added.
Does it know that two different words mean the same thing?
Not by itself. It mainly counts the words actually present.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice