Skip to content

Generative AI & LLMs

GloVe

Global Vectors for Word Representation

A method that gives words numerical descriptions by learning which words appear together across a collection of writing.

Example

Words used in similar ways receive related numerical descriptions.

Why people use it

It helps compare words using patterns of how they appear together in text.

What you'll hear

“Words with similar usage get related numerical descriptions.”

What this means for you

Check how well the teaching material covers the language and subjects you need.

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

Can it struggle when one word has several meanings?
Yes. A single stored description of a word can mix meanings that differ between sentences.
Can the source collection affect the relationships?
Yes. Different subjects and social patterns can change which words appear related.
Does a close relationship prove two words mean the same thing?
No. Words can appear in similar contexts while having different or opposite meanings.

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