AI article
Dharma Field Extractor: Any Document In, Structured Fields in JSON Out
huggingface | Nov 4, 2026 | Gabriel Pimenta de Freitas Cardoso, Paulo Henrique de Medeiros Araujo, Bruno Duarte, Francisco de Almeida Rocha Alves
Automated excerpt
A 2-billion-parameter model that extracts exactly the fields you ask for, from any document type, outperforming every frontier LLM we tested, at a fraction of the cost. You don't need the page, you need certain fields. Now a 2-billion-parameter model does it on field extraction.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.