Skip to main content

Supplier name parsed from logo instead of legal entity

Bug Report

We are seeing incorrect results for the supplier name field. The OCR returns the brand name from the page LOGO instead of the legal entity that issued the document.

Example: on a receipt the header logo reads "Make", while the actual supplier (legal entity, tied to the address and US EIN 61-1797223) is "Celonis Inc.". The API returns "Make".

What we have already tried, without success:

  • Post-processing with a RAG step

  • Adding explicit field guidance instructing the model to prefer the legal entity near the address and tax ID and to ignore header logos

Neither resolves the issue. The model still favors the visually dominant logo over the legal name in the sender block.

Questions:

  1. Is there a recommended way to make supplier_name prefer the legal entity (near supplier_address and supplier_company_registrations) instead of the header logo?

  2. Can this layout be submitted for model review or correction?

  3. If we annotate sample documents, will that improve extraction for this case?

Link to document - https://app.mindee.com/model/701fa3d9-d54b-4e7c-a506-7efed7a5079e/review?docs=98b124b8-2349-4a9a-82c6-6b7699a4a07c File name - 5dea48c8-35ad-4df5-8543-1aa1164691a2.pdf

Happy to share sample documents. Thanks for your help.

Posted by Hennadii Shevchyk ·
Status: In Progress1 comment

Log in to comment and vote

Comments1

  • Ianaré Sévi

    Team•

    Jun 3

    Hello, it looks like you are on a “pro” plan, as such you have access to the chat feature which can connect you directly to our support teams. It’s the little bubble icon on the lower left hand part of the interface.

    If you can repost this there it will be easier for you to share documents and for us to provide better support.

    Thanks!