# DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering

Source: [DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering](<https://www.sota2.com/research/paper/68fa72bd1e209131cea584d3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:33:49.815Z

Authors: Alex Nguyen, Zilong Wang, Jingbo Shang, Dheeraj Mekala

Published: 2024-03-30T18:11:39.000Z

## Abstract

The application of natural language processing models to PDF documents is pivotal for various business applications yet the challenge of training models for this purpose persists in businesses due to specific hurdles. These include the complexity of working with PDF formats that necessitate parsing text and layout information for curating training data and the lack of privacy-preserving annotation tools. This paper introduces DOCMASTER, a unified platform designed for annotating PDF documents, model training, and inference, tailored to document question-answering. The annotation interface enables users to input questions and highlight text spans within the PDF file as answers, saving layout information and text spans accordingly. Furthermore, DOCMASTER supports both state-of-the-art layout-aware and text models for comprehensive training purposes. Importantly, as annotations, training, and inference occur on-device, it also safeguards privacy. The platform has been instrumental in driving several research prototypes concerning document analysis such as the AI assistant utilized by University of California San Diego's (UCSD) International Services and Engagement Office (ISEO) for processing a substantial volume of PDF documents.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2404.00439>)

[PDF](<https://arxiv.org/pdf/2404.00439.pdf>)