01
Where this one gets misread
Which model is used matters less than who operates it, what they retain and whether it can be changed later. Those are contract questions, and they outlast whichever model is currently winning benchmarks.
Glossary
What is a large language model (LLM)?
A large language model is trained on very large text collections to predict and generate language. Who provides it and how it handles your data matter too.
Updated 21 Aug 2026
02
Questions to ask
Ask for a worked example on your own material, and the evidence needed to reproduce it.
- Which provider, under what retention terms?
- Can the model be swapped without a rebuild?
- What exactly is sent, and when?
- What happens to your behaviour at a version change?
03
How Marella uses the term
We use “Large language model (LLM)” only where a product mechanism or an evaluation method backs it up, and we say when the behaviour depends on how a deployment is configured.
- Backed by a product mechanism or an evaluation method
- Deployment differences flagged
What this page does not prove
- B1A definition is not a claim about how the product performs.
- B2Vendor implementations vary.
- B3Test the term against a representative workflow.
Related pages
Test the claim on your documents
Pick a real piece of work, agree what a good answer looks like, then go through the results together.