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

Agnese Chiatti; Sara Bernardini; Lara Shibelski Godoy Piccolo; Viola Schiaffonati; Matteo Matteucci

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

Computer Vision and Pattern Recognition 2025-05-09 v1 Artificial Intelligence Computers and Society Human-Computer Interaction Robotics

Authors: Agnese Chiatti , Sara Bernardini , Lara Shibelski Godoy Piccolo , Viola Schiaffonati , Matteo Matteucci

View on arXiv ↗ PDF ↗

Abstract

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.

Keywords

vision-language model vision-language understanding visual reasoning

Cite

@article{arxiv.2505.05318,
  title  = {Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects},
  author = {Agnese Chiatti and Sara Bernardini and Lara Shibelski Godoy Piccolo and Viola Schiaffonati and Matteo Matteucci},
  journal= {arXiv preprint arXiv:2505.05318},
  year   = {2025}
}

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

Abstract

Keywords

Cite

Related papers