It is now widely accepted that decisions made by AI systems must be explainable to their users. However, in practice, it often remains unclear how this explainability should be concretely implemented. This is especially important for nontechnical users, such as claims assessors at insurance companies, who need to understand AI system decisions and be able to explain them to customers. Think, for example, of explaining a rejected insurance claim or loan application. Although the importance of explainable AI is broadly recognized, there is often a lack of practical tools to achieve it. That’s why, in this handbook, we have combined insights from two use cases in the financial sector with findings from an extensive literature review. This has led to the identification of 30 key aspects of meaningful AI explanations. Based on these aspects, we developed a checklist to help AI developers make their systems more explainable. The checklist not only provides insight into how understandable an AI application currently is for end users, but also highlights areas for improvement.
DOCUMENT
Explainable Artificial Intelligence (XAI) aims to provide insights into the inner workings and the outputs of AI systems. Recently, there’s been growing recognition that explainability is inherently human-centric, tied to how people perceive explanations. Despite this, there is no consensus in the research community on whether user evaluation is crucial in XAI, and if so, what exactly needs to be evaluated and how. This systematic literature review addresses this gap by providing a detailed overview of the current state of affairs in human-centered XAI evaluation. We reviewed 73 papers across various domains where XAI was evaluated with users. These studies assessed what makes an explanation “good” from a user’s perspective, i.e., what makes an explanation meaningful to a user of an AI system. We identified 30 components of meaningful explanations that were evaluated in the reviewed papers and categorized them into a taxonomy of human-centered XAI evaluation, based on: (a) the contextualized quality of the explanation, (b) the contribution of the explanation to human-AI interaction, and (c) the contribution of the explanation to human- AI performance. Our analysis also revealed a lack of standardization in the methodologies applied in XAI user studies, with only 19 of the 73 papers applying an evaluation framework used by at least one other study in the sample. These inconsistencies hinder cross-study comparisons and broader insights. Our findings contribute to understanding what makes explanations meaningful to users and how to measure this, guiding the XAI community toward a more unified approach in human-centered explainability.
MULTIFILE
The transition from adolescence to adulthood also has been described as a window of opportunity or vulnerability when developmental and contextual changes converge to support positive turnarounds and redirections (Masten, Long, Kuo, McCormick, & Desjardins, 2009; Masten, Obradović, & Burt, 2006). The transition years also are a criminological crossroads, as major changes in criminal careers often occur at these ages as well. For some who began their criminal careers during adolescence, offending continues and escalates; for others involvement in crime wanes; and yet others only begin serious involvement in crime at these ages. There are distinctive patterns of offending that emerge during the transition from adolescence to adulthood. One shows a rise of offending in adolescence and the persistence of high crime rates into adulthood; a second reflects the overall age-crime curve pattern of increasing offending in adolescence followed by decreases during the transition years; and the third group shows a late onset of offending relative to the age-crime curve. Developmental theories of offending ought to be able to explain these markedly different trajectories
DOCUMENT
