new | ask | show | jobs
diptanu 3 days ago  [ - ]

There are many cases images are exported as PDFs. Think invoices or financial statements that people send to financial services companies. Using layout understanding and OCR based techniques leads to way better results than writing a parser which relies on the files metadata.

The other thing is segmenting a document and linearizing it so that an LLM can understand the content better. Layout understanding helps with figuring out the natural reading order of various blocks of the page.

dotancohen 3 days ago  [ - ]

  > There are many cases images are exported as PDFs.
One client of a client would print out her documents, then "scan" them with an Android app (actually just a photograph wrapped in a PDF). She was taught that this application is the way to create PDF files, and would staunchly not be retrained. She came up with this print-then-photograph after being told not to photograph the computer monitor - that's the furthest retraining she was able to absorb.

Be there no mistake, this woman was extremely successful at her field. Successful enough to be a client of my client. But she was taught that PDF equals that specific app, and wasn't going to change her workflow to accommodate others.