We introduce Instruction Document Visual Question Answering (iDocVQA) dataset and Large Language Document (LLaDoc) model, for training Language-Vision (LV) models for document analysis and predictions on document images, respectively. Usually, deep neural networks for the DocVQA task are trained on datasets lacking instructions. We show that using instruction-following datasets improves performance. We compare performance across document-related datasets using the recent state-of-the-art (SotA) Large Language and Vision Assistant (LLaVA)1.5 as the base model. We also evaluate the performance of the derived models for object hallucination using the Polling-based Object Probing Evaluation (POPE) dataset. The results show that instruction-tuning performance ranges from 11X to 32X of zero-shot performance and from 0.1% to 4.2% over non-instruction (traditional task) finetuning. Despite the gains, these still fall short of human performance (94.36%), implying there's much room for improvement.
@article{arxiv.2402.00453,
title = {Instruction Makes a Difference},
author = {Tosin Adewumi and Nudrat Habib and Lama Alkhaled and Elisa Barney},
journal= {arXiv preprint arXiv:2402.00453},
year = {2024}
}
Comments
Accepted at the 16th IAPR International Workshop On Document Analysis Systems (DAS)