Research
DocLang: a markup language for LLMs
IBM has introduced **DocLang**, a new markup language specifically designed for large‑language models (LLMs). Developed by lead researcher Peter Staar and IBM’s document‑parsing team, DocLang aims to
IBM has introduced DocLang, a new markup language specifically designed for large‑language models (LLMs). Developed by lead researcher Peter Staar and IBM’s document‑parsing team, DocLang aims to replace outdated or proprietary data formats with an open standard that lets generative AI more effectively access and process critical business documents. The announcement was published as part of IBM's Future Forward news series on 12 August 2026.
Related
- DocMaster: A Hierarchical Structure-Aware System for Document Analysis
- OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models
- ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization
Source: IBM Research | 2026-08-12