To achieve optimal human-system integration in the context of user-AI interaction it is important that users develop a valid representation of how AI works. In most of the everyday interaction with technical systems users construct mental models (i.e., an abstraction of the anticipated mechanisms a system uses to perform a given task). If no explicit explanations are provided by a system (e.g. by a self-explaining AI) or other sources (e.g. an instructor), the mental model is typically formed based on experiences, i.e. the observations of the user during the interaction. The congruence of this mental model and the actual systems functioning is vital, as it is used for assumptions, predictions and consequently for decisions regarding system use. A key question for human-centered AI research is therefore how to validly survey users' mental models. The objective of the present research is to identify suitable elicitation methods for mental model analysis. We evaluated whether mental models are suitable as an empirical research method. Additionally, methods of cognitive tutoring are integrated. We propose an exemplary method to evaluate explainable AI approaches in a human-centered way.
This work documents a pilot user study evaluating the effectiveness of contrastive, causal and example explanations in supporting human understanding of AI in a hypothetical commonplace human robot interaction HRI scenario. In doing so, this work situates explainable AI XAI in the context of the social sciences and suggests that HRI explanations are improved when informed by the social sciences.
Bielefeld University（比勒费尔德大学）；Honda Research Institute Europe（本田欧洲研究院）
Research in social robotics is commonly focused on designing robots that imitate human behavior. While this might increase a user's satisfaction and acceptance of robots at first glance, it does not automatically aid a non-expert user in naturally interacting with robots, and might actually hurt their ability to correctly anticipate a robot's capabilities. We argue that a faulty mental model, that the user has of the robot, is one of the main sources of confusion. In this work we investigate how communicating technical concepts of robotic systems to users affects their mental models, and how t…
Patterns vs. Patients: Evaluating LLMs against Mental Health Professionals on Personality Disorder Diagnosis through First-Person Narratives
IDEAS Research Institute（IDEAS研究 institute）；Adam Mickiewicz University（亚当·密茨凯维奇大学）；AMU Center for Artificial Intelligence（AMU人工智能中心）；Poznań University of Medical Sciences（波兹南医学科学大学）；Maria Curie-Skłodowska University（玛丽·居里-斯克洛多夫斯卡大学）
This paper presents the results of a laboratory study involving Mailvelope, a modern PGP client that integrates tightly with existing webmail providers. In our study, we brought in pairs of participants and had them attempt to use Mailvelope to communicate with each other. Our results shown that more than a decade and a half after \textit{Why Johnny Can't Encrypt}, modern PGP tools are still unusable for the masses. We finish with a discussion of pain points encountered using Mailvelope, and discuss what might be done to address them in future PGP systems.
Many interactive data systems combine visual representations of data with embedded algorithmic support for automation and data exploration. To effectively support transparent and explainable data systems, it is important for researchers and designers to know how users understand the system. We discuss the evaluation of users' mental models of system logic. Mental models are challenging to capture and analyze. While common evaluation methods aim to approximate the user's final mental model after a period of system usage, user understanding continuously evolves as users interact with a system ov…
The purpose of this paper is to develop a shared control takeover strategy for smooth and safety control transition from an automation driving system to the human driver and to approve its positive impacts on drivers' behavior and attitudes. A "human-in-the-loop" driving simulator experiment was conducted to evaluate the impact of the proposed shared control takeover strategy under different disengagement conditions. Results of thirty-two drivers showed shared control takeover strategy could improve safety performance at the aggregated level, especially at non-driving related disengagements. F…
AI Hallucination from Students' Perspective: A Thematic Analysis
Department of Computer and Information Engineering, Center for Cyber Physical Systems, Khalifa University（计算机与信息工程系，跨物理系统中心，哈利法大学）；Department of Psychology, University Malaysia Sabah（心理学系，马来西亚Sabah大学）
Beyond the Single Turn: Reframing Refusals as Dynamic Experiences Embedded in the Context of Mental Health Support Interactions with LLMs
Carnegie Mellon University（卡内基梅隆大学）；University of Washington School of Medicine（华盛顿大学医学院）；Microsoft（微软）；Harvard Medical School（哈佛医学院）；University of Washington（华盛顿大学）
MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models
Department of Artificial Intelligence, Hanyang University（翰艺大学人工智能系）；School of Computing and Information Systems, Singapore Management University（新加坡国立管理学院信息系）
Mental Imagery based Brain-Computer Interfaces (MI-BCI) enable their users to control an interface, e.g., a prosthesis, by performing mental imagery tasks only, such as imagining a right arm movement while their brain activity is measured and processed by the system. Designing and using a BCI requires users to learn how to produce different and stable patterns of brain activity for each of the mental imagery tasks. However, current training protocols do not enable every user to acquire the skills required to use BCIs. These training protocols are most likely one of the main reasons why BCIs re…
Seamless human robot interaction (HRI) and cooperative human-robot (HR) teaming critically rely upon accurate and timely human mental workload (MW) models. Cognitive Load Theory (CLT) suggests representative physical environments produce representative mental processes; physical environment fidelity corresponds with improved modeling accuracy. Virtual Reality (VR) systems provide immersive environments capable of replicating complicated scenarios, particularly those associated with high-risk, high-stress scenarios. Passive biosignal modeling shows promise as a noninvasive method of MW modeling…
Nowadays, all major web browsers have a private browsing mode. However, the mode's benefits and limitations are not particularly understood. Through the use of survey studies, prior work has found that most users are either unaware of private browsing or do not use it. Further, those who do use private browsing generally have misconceptions about what protection it provides. However, prior work has not investigated \emph{why} users misunderstand the benefits and limitations of private browsing. In this work, we do so by designing and conducting a three-part study: (1) an analytical approach co…
We conducted a lab-based eye-tracking study to investigate how the interactivity of an AI-powered fact-checking system affects user interactions, such as dwell time, attention, and mental resources involved in using the system. A within-subject experiment was conducted, where participants used an interactive and a non-interactive version of a mock AI fact-checking system and rated their perceived correctness of COVID-19 related claims. We collected web-page interactions, eye-tracking data, and mental workload using NASA-TLX. We found that the presence of the affordance of interactively manipul…
A critical analysis of cognitive load measurement methods for evaluating the usability of different types of interfaces: guidelines and framework for Human-Computer Interaction
Fly Away: Evaluating the Impact of Motion Fidelity on Optimized User Interface Design via Bayesian Optimization in Automated Urban Air Mobility Simulations
