Skip to content
LATHICAI Glossary

Generative AI & LLMs

Question answering

Using AI to answer questions from information it is given or has learned.

Example

A user asks which date appears in a provided policy.

Why people use it

It lets people ask for a particular fact without reading all the available material.

What you'll hear

“Which date does the policy give?”

What this means for you

Ask what evidence the answer used and check consequential details.

Can you control it?

Sometimes

Sometimes. Your choices depend on the tool and your access. The settings available to an everyday user may differ from those available to the people running it.

Common questions

Is every answer backed by a retrieved source?
No. Some systems answer directly from AI system behavior without consulting documents.
Should it answer when the material says nothing about the question?
It should make the missing information clear instead of inventing an answer.
Can a question contain a mistaken assumption?
Yes. A good answer may need to correct the assumption before responding.

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