01
Where this one gets misread
Tables are where document AI most often fails quietly. Merged cells, headers that repeat across pages and totals rows produce output that is well-formed, plausible and wrong.
Glossary
What is table extraction?
Table extraction turns a table into rows, columns and cells. Merged cells, headers that repeat across pages and nested layouts are where it usually breaks.
Updated 21 Aug 2026
02
Questions to ask
Ask for a worked example on your own material, and the evidence needed to reproduce it.
- What happens to a merged-cell table, and to one that spans pages?
- How is a header row identified?
- What happens to footnotes and units?
- How is a failed extraction flagged rather than guessed?
03
How Marella uses the term
We use “Table extraction” 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.