AI Briefing#document-parsing
The latest AI and developer news about #document-parsing, with the original source and a short summary.
The latest AI and developer news about #document-parsing, with the original source and a short summary.
The new benchmark uses 330+ error types to weight parsing errors by severity, correcting previous metrics that penalized formatting over factual errors.
Trace's agentic DAST covered all ten OWASP LLM risks in four days, revealing that extraction models read hidden white-on-white text as valid data.
The 1.3B parameter model uses a recursive self-improvement loop and pluggable layout analysis to convert PDFs into structured data.
Enterprise users can deploy LlamaParse in their own AWS, Azure, Google Cloud, or Kubernetes environments, with flexible options for managing model inference.
Baidu has released Unlimited-OCR 2, which uses cross-page context to parse long documents.
The working draft defines 140 rules for handling tables, forms, and diagrams to resolve inconsistencies between different parsers.
The 5B-parameter model achieves state-of-the-art results on OmniDocBench v1.6 with a score of 96.96 and supports seven distinct parsing families via a unified JSON schema.
The new platform offers token-based billing with $5 in free credits for new accounts and supports synchronous parsing for documents up to 50 pages.
In a test of 2,078 documents, PyMuPDF outperformed Docling with an overall score of 53.6 and a median processing time of 0.47 seconds per page.
Tencent has released WeVisDoc, a document parser based on Qwen3-VL, which ranked first on OmniDocBench.
Firecrawl released anydoc, a Rust library that converts 14 document formats into Markdown.
kordoc, an open-source tool that converts HWP, PDF, and Office documents to Markdown and integrates with AI agents as an MCP server, has been released.
PaddlePaddle has released HPD-Parsing, a 1B document parsing model based on hierarchical parallel decoding, achieving the top score of 94.91% on OmniDocBench v1.6.
Task-specific routing built by teams with deep expertise in a particular task outperforms general-purpose routers on both cost and accuracy.
A lightweight end-to-end document structuring OCR model based on Qwen3.5-0.8B has been released.
A 3.3B-parameter open-source OCR model capable of parsing entire documents from single images to PDFs has been released.
Baidu has released Unlimited-OCR, a new OCR model that processes long documents and multi-page content in one go.
PaddleOCR 3.5 has added Transformers backend support.
Ran LiteParse in the browser to build a PDF text extraction web app that even supports OCR.
ParseBench is a benchmark that evaluates parser accuracy on your own documents using 5 metrics.