Skip to content

Generative AI & LLMs

Information extraction

Pulling specific details from material and putting them into organized fields, such as names and dates.

Example

A tool extracts dates, organizations and amounts from contracts.

Why people use it

It turns long or messy material into information people can sort and use.

What you'll hear

“Pull out the dates and amounts.”

What this means for you

Check both extraction accuracy and the reliability of the original material.

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 extraction check whether the source facts are true?
No. It identifies information in the source, which can itself be incorrect.
Can it confuse who did what?
Yes. Complex sentences or repeated names can lead it to connect a fact to the wrong person.
What happens when a field is absent?
A good system marks it missing. Some systems instead guess, which can create a false record.

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