Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chiatti, Agnese, Bernardini, Sara, Piccolo, Lara Shibelski Godoy, Schiaffonati, Viola, Matteucci, Matteo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910933070118912
author Chiatti, Agnese
Bernardini, Sara
Piccolo, Lara Shibelski Godoy
Schiaffonati, Viola
Matteucci, Matteo
author_facet Chiatti, Agnese
Bernardini, Sara
Piccolo, Lara Shibelski Godoy
Schiaffonati, Viola
Matteucci, Matteo
contents The rapid adoption of Vision Language Models (VLMs), pre-trained on large image-text and video-text datasets, calls for protecting and informing users about when to trust these systems. This survey reviews studies on trust dynamics in user-VLM interactions, through a multi-disciplinary taxonomy encompassing different cognitive science capabilities, collaboration modes, and agent behaviours. Literature insights and findings from a workshop with prospective VLM users inform preliminary requirements for future VLM trust studies.
format Preprint
id arxiv_https___arxiv_org_abs_2505_05318
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects
Chiatti, Agnese
Bernardini, Sara
Piccolo, Lara Shibelski Godoy
Schiaffonati, Viola
Matteucci, Matteo
Computer Vision and Pattern Recognition
Artificial Intelligence
Computers and Society
Human-Computer Interaction
Robotics
The rapid adoption of Vision Language Models (VLMs), pre-trained on large image-text and video-text datasets, calls for protecting and informing users about when to trust these systems. This survey reviews studies on trust dynamics in user-VLM interactions, through a multi-disciplinary taxonomy encompassing different cognitive science capabilities, collaboration modes, and agent behaviours. Literature insights and findings from a workshop with prospective VLM users inform preliminary requirements for future VLM trust studies.
title Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computers and Society
Human-Computer Interaction
Robotics
url https://arxiv.org/abs/2505.05318