Skip to content

Generative AI & LLMs

Natural language understanding

Computer methods for working out what someone's words mean or what they are asking for.

Example

A system interprets 'move it to Friday' using the conversation's background information.

Why people use it

It helps software work out what a person means, not just which words appear.

What you'll hear

“It needs to understand what 'move it' refers to.”

What this means for you

Test ambiguous phrasing and whether the system asks useful clarifying questions.

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 the name mean the computer has human awareness?
No. It describes a practical ability to interpret language, rather than proof of human-like experience.
Why can sarcasm be difficult?
The intended meaning can differ from the literal words and depend on shared background information.
Can an unclear request have several reasonable meanings?
Yes. Sometimes asking a follow-up is more useful than making a confident guess.

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