Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Irawan, Patrick Amadeus, Winata, Genta Indra, Cahyawijaya, Samuel, Purwarianti, Ayu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909420341952512
author Irawan, Patrick Amadeus
Winata, Genta Indra
Cahyawijaya, Samuel
Purwarianti, Ayu
author_facet Irawan, Patrick Amadeus
Winata, Genta Indra
Cahyawijaya, Samuel
Purwarianti, Ayu
contents Natural Language Explanation (NLE) aims to elucidate the decision-making process by providing detailed, human-friendly explanations in natural language. It helps demystify the decision-making processes of large vision-language models (LVLMs) through the use of language models. While existing methods for creating a Vision Question-Answering with Natural Language Explanation (VQA-NLE) datasets can provide explanations, they heavily rely on human annotations that are time-consuming and costly. In this study, we propose a novel approach that leverages LVLMs to efficiently generate high-quality synthetic VQA-NLE datasets. By evaluating our synthetic data, we showcase how advanced prompting techniques can lead to the production of high-quality VQA-NLE data. Our findings indicate that this proposed method achieves up to 20x faster than human annotation, with only a minimal decrease in qualitative metrics, achieving robust quality that is nearly equivalent to human-annotated data. Furthermore, we show that incorporating visual prompts significantly enhances the relevance of text generation. Our study paves the way for a more efficient and robust automated generation of multi-modal NLE data, offering a promising solution to the problem.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14785
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language Models
Irawan, Patrick Amadeus
Winata, Genta Indra
Cahyawijaya, Samuel
Purwarianti, Ayu
Computation and Language
Computer Vision and Pattern Recognition
Natural Language Explanation (NLE) aims to elucidate the decision-making process by providing detailed, human-friendly explanations in natural language. It helps demystify the decision-making processes of large vision-language models (LVLMs) through the use of language models. While existing methods for creating a Vision Question-Answering with Natural Language Explanation (VQA-NLE) datasets can provide explanations, they heavily rely on human annotations that are time-consuming and costly. In this study, we propose a novel approach that leverages LVLMs to efficiently generate high-quality synthetic VQA-NLE datasets. By evaluating our synthetic data, we showcase how advanced prompting techniques can lead to the production of high-quality VQA-NLE data. Our findings indicate that this proposed method achieves up to 20x faster than human annotation, with only a minimal decrease in qualitative metrics, achieving robust quality that is nearly equivalent to human-annotated data. Furthermore, we show that incorporating visual prompts significantly enhances the relevance of text generation. Our study paves the way for a more efficient and robust automated generation of multi-modal NLE data, offering a promising solution to the problem.
title Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language Models
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.14785