A new document-pretrained transformer targets tables that break parsers
- Source
- x.com
- Date
Announcing a significant upgrade to Agentic Document Extraction! LandingAI's new DPT (Document Pre-trained Transformer) accurately extracts even from complex docs. For example, from large, complex tables, which is important for many finance and healthcare applications. And a new SDK makes using it require only 3 simple lines of code. Please see the video for technical details. I hope this unlocks a lot of value from the "dark data" currently stuck in PDF files, and that you'll build something cool with this!
Context
LandingAI's September 30, 2025 announcement introduced DPT-2, a document-processing model aimed at difficult layouts, including tables with merged cells or missing gridlines. The company says it preserves table structure and links extracted values to their source cells, giving users a way to check where a returned figure came from.
This addresses a different part of document processing from field extraction, where users specify which values they want returned. The announcement treats parsing a document and extracting schema-defined fields as separate offerings. It establishes the company's claimed capability, without quantifying accuracy across financial or medical documents.
- transformer — The neural network architecture behind modern AI models, built on attention — letting every word directly consider every other word in parallel.
Checking sign-in…
Loading comments…