Document Automation Extraction consistently getting wrong text values

Forum|Forum|5 months ago
March 4, 2026
15 replies
244 views

I am getting a supplier’s invoice document consistently extracted incorrectly.

The invoice PO number is listed as 20493307.

The extracted text is always 00439307.

The 2 becomes a 0 and the 93 becomes 39.

The rest of the text in the description field is correct. only the PO has this issue.

When I view this in validator, the validation recognizes the correct value for that field.

Any tricks I can try for fixing this?

I have tried swapping the OCR engine in my learning instance, but it doesn’t appear to have any affect.

Best answer by Aaron.Gleason

@sleemand I think you’ve hit the nail on the head. I checked with our engineering team and they said the “GenAIVision” tag, if used for that field, could cause this issue.

You could switch to a newer AI model like Gemini. There will also be some enhancements in the near future, so watch the release notes on our docs site.

https://docs.automationanywhere.com/bundle/enterprise-v2019/page/enterprise-cloud/topics/release-notes/cloud-release-notes.html

Show previous replies

S

sleemandAuthor

Navigator | Tier 3

@Aaron.Gleason

Is AI heuristic feedback tied to the model chosen here?

I have already split out a different supplier’s invoices to a new learning instance using Anthropic which instantly solved my problems from my OpenAI instance with that supplier.

I’m wondering if in my testing, all the feedback got reset by switching model providers and the 35k documents we’ve processed were negatively influencing this behavior.

Aaron.Gleason

Automation Anywhere Team

@sleemand I certainly hope not, but that is a possibility. 🤔

Either way, the direct text extraction should have eliminated the problem, unless AI goes afterwards and tries to “autocorrect” the entries...

S

sleemandAuthor

Navigator | Tier 3

@Aaron.Gleason

That was my suspicion. It is almost like it is hallucinating the value.

I re-ran that file with trace logging and pulled up the debug files.

From what I think I understand in these files, the OCR detects it properly.

But the extracted data is incorrect.

Aaron.GleasonAnswer

Automation Anywhere Team

@sleemand I think you’ve hit the nail on the head. I checked with our engineering team and they said the “GenAIVision” tag, if used for that field, could cause this issue.

You could switch to a newer AI model like Gemini. There will also be some enhancements in the near future, so watch the release notes on our docs site.

https://docs.automationanywhere.com/bundle/enterprise-v2019/page/enterprise-cloud/topics/release-notes/cloud-release-notes.html

S

sleemandAuthor

Navigator | Tier 3

@Aaron.Gleason

I am using the GenAIVision tag since that solved some of my other issues with table data extraction.

I’ll be doing some tests with the other models to see how it impacts the rest of the documents I’ve been struggling with too.

Thanks for the assistance here.