Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects
It addresses the need to inform and protect users in VLM interactions, but is incremental as a survey.
This survey reviews research on user trust in Vision Language Models (VLMs), analyzing trust dynamics through a multi-disciplinary taxonomy and proposing preliminary requirements for future studies based on literature and user workshops.
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.