评估对人类-人工智能交互的健康不信任:解释视觉注意力的变化
Tobias M Peters1, Kai Biermeier1, Ingrid Scharlau1
1Department of Psychology, Faculty of Arts and Humanities, Paderborn University, Paderborn, Germany.
这项研究探讨了人与人工智能的相互作用,探讨了适当的信任和健康的不信任. 隐蔽的视觉注意力,而不仅仅是信任和依赖,被检查为一个关键指标. 错误分类影响了注意力能力,但不一定影响判断力.
科学领域:
- 人与计算机的交互
- 认知心理学 认知心理学
- 人工智能伦理学 人工智能伦理学
背景情况:
- 对人工智能 (AI) 的适当信任对于有效的人类-AI合作至关重要.
- 目前评估信任和依赖的方法不足以衡量适当的信任和健康的不信任.
- 隐蔽的视觉注意力为评估人类对人工智能的反应提供了一个新的视角.
研究的目的:
- 引入和测试隐藏的视觉注意力作为对AI适当信任的额外指标.
- 探索视觉注意力和对人类-人工智能交互的健康不信任之间的关系.
- 评估当前信任和依赖指标的充分性.
主要方法:
- 使用视觉注意力理论来正式化视觉注意力.
- 使用时间顺序判断测量了对AI分类的注意力和重量.
- 利用图像分类任务与模拟AI分类 (正确和不正确).
主要成果:
- 与正确的分类相比,人工智能错误分类降低了注意力能力.
- 这种注意力减弱并没有改善后来的分类判断.
- 注意力加权受到刺激难度的影响,而不是分类正确性.
结论:
- 隐藏的视觉注意力显示出潜在的潜力,作为适当的信任和对人类-AI互动的健康不信任的指标.
- 视觉注意力指标可能会提供比传统的信任和依赖措施更深入的见解.
- 需要进一步的研究才能充分理解视觉注意力对人类-人工智能信任动态的影响.
相关概念视频
06:46Investigating the Deployment of Visual Attention Before Accurate and Averaging Saccades via Eye Tracking and Assessment of Visual Sensitivity
Visual Attention: fMRI Investigation of Object-based Attentional Control
The human visual system is incredibly sophisticated and capable of processing large amounts of information very quickly. However, the brain's capacity to process information is not an unlimited resource. Attention, the ability to selectively process information that is relevant to current goals and to ignore information that is not, is therefore an essential part of visual perception. Some...
07:20Human Colonoid Monolayers to Study Interactions Between Pathogens, Commensals, and Host Intestinal Epithelium
09:44Methods to Test Visual Attention Online
13:00Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments
The Attentional Blink
In order for recognition of a certain stimulus to take place, visual attention needs to be directed towards said stimulus. To the earliest parts of the visual system, objects are not objects, they are collections of visual features-lines, corners, changes in texture, color, and light. Attention is the resource that is necessary for later processing in order to recognize what a given bundle of features adds up to. This makes...


