01
Where this one gets misread
Quoted alone, either number is meaningless. Perfect precision is available to anyone willing to return a single result. Both need the reference set and somebody's definition of relevant attached.
Glossary
What is recall and precision?
Recall is the share of relevant items a system found; precision is the share of what it found that was relevant. Neither counts until you define relevant.
By Marella AI · Updated 21 Aug 2026
02
Questions to ask
Ask for a worked example on your own material, and the evidence needed to reproduce it.
- Measured against which reference set?
- Who judged relevance, and by what rule?
- Where is the trade-off set, and can you change it?
- What does the whole curve look like, not the one point?
03
How Marella uses the term
We use “Recall and precision” 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
Caveats
- B1A definition is not a claim about how the product performs.
- B2Vendor implementations vary.
- B3Test the term against a representative workflow.
Related pages
Test it on your own documents
Pick a real piece of work, agree what a good answer looks like, then go through the results together.