# DocPrompt: Large-scale continue pretrain for zero-shot and few-shot document question answering

arXiv: https://arxiv.org/abs/2308.10959 · HTML: https://mlsanity.com/paper/2308.10959/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 12 references that are in the map.
- First posted on arXiv 21 Aug 2023.

## Builds on (most cited first, 2 of 2)

- [LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding](https://mlsanity.com/paper/2104.08836/) (2021)
- [ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding](https://mlsanity.com/paper/2209.08569/) (2022)

## Abstract (arXiv)

In this paper, we propose Docprompt for document question answering tasks with powerful zero-shot and few-shot performance. We proposed a novel weakly supervised data generation method, a novel multl-stage training method and a novel understanding model & generation model ensemble method. We achieved state-of-the-art performance on 4 document question answering tasks. This method greatly improves the delivery efficiency and model performance of document question answering customer projects, reducing annotation costs and labor costs. Our demo can be found at https://huggingface.co/spaces/PaddlePaddle/ERNIE-Layout.