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.