VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Zhe, Ren, Yixiao, Li, Jing, Yin, Yu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929535173263360
author Hu, Zhe
Ren, Yixiao
Li, Jing
Yin, Yu
author_facet Hu, Zhe
Ren, Yixiao
Li, Jing
Yin, Yu
contents Large vision language models (VLMs) have demonstrated significant potential for integration into daily life, making it crucial for them to incorporate human values when making decisions in real-world situations. This paper introduces VIVA, a benchmark for VIsion-grounded decision-making driven by human VAlues. While most large VLMs focus on physical-level skills, our work is the first to examine their multimodal capabilities in leveraging human values to make decisions under a vision-depicted situation. VIVA contains 1,240 images depicting diverse real-world situations and the manually annotated decisions grounded in them. Given an image there, the model should select the most appropriate action to address the situation and provide the relevant human values and reason underlying the decision. Extensive experiments based on VIVA show the limitation of VLMs in using human values to make multimodal decisions. Further analyses indicate the potential benefits of exploiting action consequences and predicted human values.
format Preprint
id arxiv_https___arxiv_org_abs_2407_03000
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values
Hu, Zhe
Ren, Yixiao
Li, Jing
Yin, Yu
Computation and Language
Computer Vision and Pattern Recognition
Large vision language models (VLMs) have demonstrated significant potential for integration into daily life, making it crucial for them to incorporate human values when making decisions in real-world situations. This paper introduces VIVA, a benchmark for VIsion-grounded decision-making driven by human VAlues. While most large VLMs focus on physical-level skills, our work is the first to examine their multimodal capabilities in leveraging human values to make decisions under a vision-depicted situation. VIVA contains 1,240 images depicting diverse real-world situations and the manually annotated decisions grounded in them. Given an image there, the model should select the most appropriate action to address the situation and provide the relevant human values and reason underlying the decision. Extensive experiments based on VIVA show the limitation of VLMs in using human values to make multimodal decisions. Further analyses indicate the potential benefits of exploiting action consequences and predicted human values.
title VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.03000