Skip to content

AI Foundations

Positional encoding

Information that helps AI keep track of where pieces appear or their order.

Example

A transformer receives signals that help distinguish the order of words.

Why people use it

It helps an AI system distinguish order rather than treat pieces as an unordered collection.

What you'll hear

“How does it know which word came first?”

What this means for you

Check which method and sequence-length limits the AI system uses.

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 a system track relative order rather than exact position?
Yes. Some methods focus on how far apart pieces are, rather than assigning each a fixed position number.
Why does word order matter?
The same words in a different order can express a different meaning.
Can a system struggle with longer sequences than it learned on?
Yes. Some position-handling methods work less reliably outside the lengths they were designed or trained for.

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