Search for: All records

The need for interpretable and accountable intelligent systems grows along with the prevalence of artificial intelligence ( AI ) applications used in everyday life. Explainable AI ( XAI ) systems are intended to self-explain the reasoning behind system decisions and predictions. Researchers from different disciplines work together to define, design, and evaluate explainable systems. However, scholars from different disciplines focus on different objectives and fairly independent topics of XAI research, which poses challenges for identifying appropriate design and evaluation methodology and consolidating knowledge across efforts. To this end, this article presents a survey and framework intended to share knowledge and experiences of XAI design and evaluation methods across multiple disciplines. Aiming to support diverse design goals and evaluation methods in XAI research, after a thorough review of XAI related papers in the fields of machine learning, visualization, and human-computer interaction, we present a categorization of XAI design goals and evaluation methods. Our categorization presents the mapping between design goals for different XAI user groups and their evaluation methods. From our findings, we develop a framework with step-by-step design guidelines paired with evaluation methods to close the iterative design and evaluation cycles in multidisciplinary XAI teams. Further, we provide summarized ready-to-use tables of evaluation methods and recommendations for different goals in XAI research. 

While EXplainable Artificial Intelligence (XAI) approaches aim to improve human-AI collaborative decision-making by improving model transparency and mental model formations, experiential factors associated with human users can cause challenges in ways system designers do not anticipate. In this paper, we first showcase a user study on how anchoring bias can potentially affect mental model formations when users initially interact with an intelligent system and the role of explanations in addressing this bias. Using a video activity recognition tool in cooking domain, we asked participants to verify whether a set of kitchen policies are being followed, with each policy focusing on a weakness or a strength. We controlled the order of the policies and the presence of explanations to test our hypotheses. Our main finding shows that those who observed system strengths early-on were more prone to automation bias and made significantly more errors due to positive first impressions of the system, while they built a more accurate mental model of the system competencies. On the other hand, those who encountered weaknesses earlier made significantly fewer errors since they tended to rely more on themselves, while they also underestimated model competencies due to having a more negative first impression of the model. Motivated by these findings and similar existing work, we formalize and present a conceptual model of user’s past experiences that examine the relations between user’s backgrounds, experiences, and human factors in XAI systems based on usage time. Our work presents strong findings and implications, aiming to raise the awareness of AI designers towards biases associated with user impressions and backgrounds. 

In emergency events, first responders often have to build an accurate spatial working memory of unfamiliar spaces in a short time period. This study investigates the impact of information format on first responders’ short-term spatial memory of large-scale spaces via a human-subject experiment (n=63). A virtual model was created to simulate a real building on Texas A&M University campus. A total of 28 building components were modified in the virtual model. Participants were asked to review the virtual model with one of the three methods: 2D drawing, 3D model, and VR model. After the review session, the participants were sent to the real building to identify the discrepancies, and accuracy was documented as the performance measure. The results reveal that the 3D and VR groups both significantly outperformed the 2D group in spatial working memory. This study sets the foundation to further understand how instructional information affects the performance of first responders in emergency response.