20 October 2021 in The Knowledge Engineering Review
This paper presents a model of contrastive explanation using structural casual models. The topic of causal explanation in artificial intelligence has gathered interest in recent years as researchers and practitioners aim to increase trust and understanding of intelligent decision-making. While different sub-fields of artificial intelligence have looked into this problem with a sub-field-specific view, there are few models that aim to capture explanation more generally. One general model is based on structural causal models . It defines an explanation as a fact that, if found to be true, would constitute an actual cause of a specific event. However, research in philosophy and social sciences shows that explanations are contrastive : that is, when people ask for an explanation of an event—the fact —they (sometimes implicitly) are asking for an explanation relative to some contrast case ; that is, ‘Why P rather than Q ?’. In this paper, we extend the structural causal model approach to define two complementary notions of contrastive explanation , and demonstrate them on two classical problems in artificial intelligence: classification and planning. We believe that this model can help researchers in subfields of artificial intelligence to better understand contrastive explanation.
4 May 2025 in Australian Journal of Management
We face the situation of radical change in work due to advances in AI and related digital technologies, with uncertainty about how this change will affect workers’ opportunities for meaningful work designs, as well as the flow-on effects for worker well-being, health, skills and productivity. A ‘technocentric fallacy’ assumes that technology itself is the primary driver of successful digital transformation. Yet we have learned from history that technological considerations alone are insufficient for human well-being and productivity. The long-established sociotechnical systems theory of work design advocates that the social aspects of work (e.g. leadership, culture, task allocations) and technical aspects of work (e.g. AI, robots) need to be jointly optimised to achieve quality work. In this article, we expand this theoretical approach to fit current challenges, and to enable its wider-scale application. Our team of social and technical scholars propose a ‘co-evolving’ sociotechnical systems’ (CeSTS) approach to the design, implementation, and use of digital technology in work contexts. CeSTS expands thinking across time and across levels of analysis to create a more proactive, and ultimately more balanced, approach. Achieving CeSTS requires interdisciplinary collaboration, methods that can track dynamic and emergent change, and a multi-stakeholder approach that both informs research and shapes change in work. Altogether, the radical changes in technology demand an equally radical shift in how scholars investigate, and ultimately help to shape, future work. JEL Classification: 033
8 December 2023 in ACM Transactions on Interactive Intelligent Systems
In this article, we show that explanations of decisions made by machine learning systems can be improved by not only explainingwhya decision was made but also explaininghowan individual could obtain their desired outcome. We formally define the concept ofdirective explanations(those that offer specific actions an individual could take to achieve their desired outcome), introduce two forms of directive explanations (directive-specific and directive-generic), and describe how these can be generated computationally. We investigate people’s preference for and perception toward directive explanations through two online studies, one quantitative and the other qualitative, each covering two domains (the credit scoring domain and the employee satisfaction domain). We find a significant preference for both forms of directive explanations compared to non-directive counterfactual explanations. However, we also find that preferences are affected by many aspects, including individual preferences and social factors. We conclude that deciding what type of explanation to provide requires information about the recipients and other contextual information. This reinforces the need for a human-centered and context-specific approach to explainable AI.
17 July 2023 in KI - Künstliche Intelligenz
This paper summarizes the psychological insights and related design challenges that have emerged in the field of Explainable AI (XAI). This summary is organized as a set of principles, some of which have recently been instantiated in XAI research. The primary aspects of implementation to which the principles refer are the design and evaluation stages of XAI system development, that is, principles concerning the design of explanations and the design of experiments for evaluating the performance of XAI systems. The principles can serve as guidance, to ensure that AI systems are human-centered and effectively assist people in solving difficult problems.
21 July 2022 in Journal of Biomedical Informatics