InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions
This work addresses the challenge of zero-shot generalization in visual document understanding for researchers and practitioners, representing a novel method for a known bottleneck.
The authors tackled the problem of completing visual document understanding tasks using human-written instructions by creating InstructDoc, a large-scale dataset of 30 VDU datasets with diverse instructions, and designing InstructDr, an instruction-based model that outperforms existing multimodal LLMs and ChatGPT without specific training.
We study the problem of completing various visual document understanding (VDU) tasks, e.g., question answering and information extraction, on real-world documents through human-written instructions. To this end, we propose InstructDoc, the first large-scale collection of 30 publicly available VDU datasets, each with diverse instructions in a unified format, which covers a wide range of 12 tasks and includes open document types/formats. Furthermore, to enhance the generalization performance on VDU tasks, we design a new instruction-based document reading and understanding model, InstructDr, that connects document images, image encoders, and large language models (LLMs) through a trainable bridging module. Experiments demonstrate that InstructDr can effectively adapt to new VDU datasets, tasks, and domains via given instructions and outperforms existing multimodal LLMs and ChatGPT without specific training.