The Flow has not summarised this story yet — read it at arXiv Computation and Language.
The paper evaluates open-source OCR, LLM, and VLM systems on a high‑risk public sector task: extracting structured data from student application documents. Results show that VLMs generally outperform OCR+LLM pipelines, yet only 4 of 35 configurations achieve F1 scores above 0.5, with most combinations scoring below 0.25. Model size and input quality, especially preserving OCR structure, are critical factors influencing performance.
arXiv:2607. 29677v1 Announce Type: new Abstract: Enterprise workflows increasingly rely on agents for \emph{schema-guided extraction}: given a document and a user-defined schema, the agent faithfully follows the schema to produce the correct output with source evidence as grounding metadata.
arXiv:2608. 06607v1 Announce Type: cross Abstract: Most document-extraction systems use a single model for all documents.
arXiv:2607. 16203v1 Announce Type: cross Abstract: Document parsing is a foundational step for document understanding tasks such as visual question answering and key information extraction, as it transforms unstructured scanned images into structured representations by extracting textual, visual, and layout information.
arXiv:2608.20868v1 Announce Type: cross Abstract: Document processing pipelines traditionally cascade optical character recognition (OCR) engines with downstream models for structured information ext...
arXiv:2608. 12133v1 Announce Type: new Abstract: Enterprise guideline documents are heterogeneous and multimodal, combining narrative text, complex tables, and embedded images.