Home/Events/Dharma Field Extractor: Any Document In, Structured Fields in JSON Out

Dharma Field Extractor: Any Document In, Structured Fields in JSON Out

Confirmed
Confidence
90%
Impact: 80%
Updated 11m ago

Consensus Brief

The Dharma Field Extractor is a 2-billion-parameter model designed to extract specific fields from various document types and return them in structured JSON format. It outperforms general-purpose LLMs in field extraction tasks while being more cost-effective. The model can operate with or without a predefined schema for the fields to be extracted.

Sourced from
Primary: Hugging Face

What Changed Since Last Update

11m ago

New official source added: Hugging Face published an update on Wed, 04 No ("Dharma Field Extractor: Any Document In, Structured Fields in JSON Out").

Claim Ledger

4 claims tracked across sources

Official Claim

The Field Extractor outperforms every frontier LLM tested at a fraction of the cost.

Confirmed Fact

The model is trained on 43,384 examples covering both open and schema-directed request modes.

Confirmed Fact

The benchmark covers 546 documents across three request scenarios for a total of 1,638 cases.

Official Claim

Cost runs from roughly 6 times lower to roughly 147 times lower compared to general-purpose LLMs.

Role-Based Impact Analysis