BloomVQA: Assessing Hierarchical Multi-modal Comprehension

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gong, Yunye, Shrestha, Robik, Claypoole, Jared, Cogswell, Michael, Ray, Arijit, Kanan, Christopher, Divakaran, Ajay
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909220031430656
author Gong, Yunye
Shrestha, Robik
Claypoole, Jared
Cogswell, Michael
Ray, Arijit
Kanan, Christopher
Divakaran, Ajay
author_facet Gong, Yunye
Shrestha, Robik
Claypoole, Jared
Cogswell, Michael
Ray, Arijit
Kanan, Christopher
Divakaran, Ajay
contents We propose a novel VQA dataset, BloomVQA, to facilitate comprehensive evaluation of large vision-language models on comprehension tasks. Unlike current benchmarks that often focus on fact-based memorization and simple reasoning tasks without theoretical grounding, we collect multiple-choice samples based on picture stories that reflect different levels of comprehension, as laid out in Bloom's Taxonomy, a classic framework for learning assessment widely adopted in education research. Our data maps to a novel hierarchical graph representation which enables automatic data augmentation and novel measures characterizing model consistency. We perform graded evaluation and reliability analysis on recent multi-modal models. In comparison to low-level tasks, we observe decreased performance on tasks requiring advanced comprehension and cognitive skills with up to 38.0\% drop in VQA accuracy. In comparison to earlier models, GPT-4V demonstrates improved accuracy over all comprehension levels and shows a tendency of bypassing visual inputs especially for higher-level tasks. Current models also show consistency patterns misaligned with human comprehension in various scenarios, demonstrating the need for improvement based on theoretically-grounded criteria.
format Preprint
id arxiv_https___arxiv_org_abs_2312_12716
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle BloomVQA: Assessing Hierarchical Multi-modal Comprehension
Gong, Yunye
Shrestha, Robik
Claypoole, Jared
Cogswell, Michael
Ray, Arijit
Kanan, Christopher
Divakaran, Ajay
Computer Vision and Pattern Recognition
Computation and Language
Machine Learning
We propose a novel VQA dataset, BloomVQA, to facilitate comprehensive evaluation of large vision-language models on comprehension tasks. Unlike current benchmarks that often focus on fact-based memorization and simple reasoning tasks without theoretical grounding, we collect multiple-choice samples based on picture stories that reflect different levels of comprehension, as laid out in Bloom's Taxonomy, a classic framework for learning assessment widely adopted in education research. Our data maps to a novel hierarchical graph representation which enables automatic data augmentation and novel measures characterizing model consistency. We perform graded evaluation and reliability analysis on recent multi-modal models. In comparison to low-level tasks, we observe decreased performance on tasks requiring advanced comprehension and cognitive skills with up to 38.0\% drop in VQA accuracy. In comparison to earlier models, GPT-4V demonstrates improved accuracy over all comprehension levels and shows a tendency of bypassing visual inputs especially for higher-level tasks. Current models also show consistency patterns misaligned with human comprehension in various scenarios, demonstrating the need for improvement based on theoretically-grounded criteria.
title BloomVQA: Assessing Hierarchical Multi-modal Comprehension
topic Computer Vision and Pattern Recognition
Computation and Language
Machine Learning
url https://arxiv.org/abs/2312.12716