It is widely acknowledged that transparency of automated decision making is crucial for deployability of intelligent systems, and explaining the reasons why some decisions are "good" and some are not is a way to achieving this transparency. We consider two variants of decision making, where "good" decisions amount to alternatives (i) meeting "most" goals, and (ii) meeting "most preferred" goals. We then define, for each variant and notion of "goodness" (corresponding to a number of existing notions in the literature), explanations in two formats, for justifying the selection of an alternative to audiences with differing needs and competences: lean explanations, in terms of goals satisfied and, for some notions of "goodness", alternative decisions, and argumentative explanations, reflecting the decision process leading to the selection, while corresponding to the lean explanations. To define argumentative explanations, we use assumption-based argumentation (ABA), a well-known form of structured argumentation. Specifically, we define ABA frameworks such that "good" decisions are admissible ABA arguments and draw argumentative explanations from dispute trees sanctioning this admissibility. Finally, we instantiate our overall framework for explainable decision-making to accommodate connections between goals and decisions in terms of decision graphs incorporating defeasible and non-defeasible information.

The rising popularity of explainable artificial intelligence (XAI) to understand high-performing black boxes, also raised the question of how to evaluate explanations of machine learning (ML) models. While interpretability and explainability are often presented as a subjectively validated binary property, we consider it a multi-faceted concept. We identify 12 conceptual properties, such as Compactness and Correctness, that should be evaluated for comprehensively assessing the quality of an explanation. Our so-called Co-12 properties serve as categorization scheme for systematically reviewing the evaluation practice of more than 300 papers published in the last 7 years at major AI and ML conferences that introduce an XAI method. We find that 1 in 3 papers evaluate exclusively with anecdotal evidence, and 1 in 5 papers evaluate with users. We also contribute to the call for objective, quantifiable evaluation methods by presenting an extensive overview of quantitative XAI evaluation methods. This systematic collection of evaluation methods provides researchers and practitioners with concrete tools to thoroughly validate, benchmark and compare new and existing XAI methods. This also opens up opportunities to include quantitative metrics as optimization criteria during model training in order to optimize for accuracy and interpretability simultaneously.

Intelligent decision support (IDS) systems leverage artificial intelligence techniques to generate recommendations that guide human users through the decision making phases of a task. However, a key challenge is that IDS systems are not perfect, and in complex real-world scenarios may produce incorrect output or fail to work altogether. The field of explainable AI planning (XAIP) has sought to develop techniques that make the decision making of sequential decision making AI systems more explainable to end-users. Critically, prior work in applying XAIP techniques to IDS systems has assumed that the plan being proposed by the planner is always optimal, and therefore the action or plan being recommended as decision support to the user is always correct. In this work, we examine novice user interactions with a non-robust IDS system -- one that occasionally recommends the wrong action, and one that may become unavailable after users have become accustomed to its guidance. We introduce a novel explanation type, subgoal-based explanations, for planning-based IDS systems, that supplements traditional IDS output with information about the subgoal toward which the recommended action would contribute. We demonstrate that subgoal-based explanations lead to improved user task performance, improve user ability to distinguish optimal and suboptimal IDS recommendations, are preferred by users, and enable more robust user performance in the case of IDS failure

Dramatic success in machine learning has created an explosion of new AI capabilities. Continued advances promise to produce autonomous systems that perceive, learn, decide, and act on their own. These systems offer tremendous benefits, but their effectiveness will be limited by the machine's inability to explain its decisions and actions to human users. This issue is especially important for the United States Department of Defense (DoD), which faces challenges that require the development of more intelligent, autonomous, and reliable systems. XAI will be essential for users to understand, appropriately trust, and effectively manage this emerging generation of artificially intelligent partners.

Artificial Intelligence (AI) continues to fascinate and rule the world of data science. It has been the one technology that had impacted the maximum number of domains in the last 10 years – and apparently, will continue doing so throughout the current decade. Coupled with Machine Learning (ML), AI-based algorithms have proved to be a game changer in data-based decision-making and predictive models. However, for business value and critical operations, AI algorithms cannot function as an inscrutable black box or operate entirely autonomously without any kind of check point. It is now expected that organizations developing and/or implementing complex AI systems need to factor in explainability into their models to eliminate future complications.

Dr. Henderson Lewis Jr. explains the reasoning behind a vaccine mandate for students ages 5 and up on'America Reports.' COVID-19 during pregnancy surprisingly did not increase the chance of babies' neurodevelopmental delay, although those born during the pandemic were associated with higher neurodevelopmental delays compared to those born prior to the pandemic, according to a recent JAMA Pediatrics study. Columbia University Irving Medical Center established a prospective cohort study called COVID-19 Mother Baby Outcomes (COMBO) Initiative in the spring of 2020 to study the associations between the exposure of the virus while the baby is still in the mother's womb with the well-being of the baby. The researchers studied a cohort of infants who were exposed to COVID-19 during pregnancy and compared them to a control group of similar gestational age at birth, birthday, sex, and mode of delivery who were not exposed to the virus. Whether or not kids should be required to wear masks has been a polarizing topic thorough the COVID-19 pandemic. "Infants born to mothers who have viral infections during pregnancy have a higher risk of neurodevelopmental deficits, so we thought we would find some changes in the neurodevelopment of babies whose mothers had COVID during pregnancy," said lead investigator Dr. Dani Dumitriu.

One principal impediment in the successful deployment of AI-based Computer-Aided Diagnosis (CAD) systems in clinical workflows is their lack of transparent decision making. Although commonly used eXplainable AI methods provide some insight into opaque algorithms, such explanations are usually convoluted and not readily comprehensible except by highly trained experts. The explanation of decisions regarding the malignancy of skin lesions from dermoscopic images demands particular clarity, as the underlying medical problem definition is itself ambiguous. This work presents ExAID (Explainable AI for Dermatology), a novel framework for biomedical image analysis, providing multi-modal concept-based explanations consisting of easy-to-understand textual explanations supplemented by visual maps justifying the predictions. ExAID relies on Concept Activation Vectors to map human concepts to those learnt by arbitrary Deep Learning models in latent space, and Concept Localization Maps to highlight concepts in the input space. This identification of relevant concepts is then used to construct fine-grained textual explanations supplemented by concept-wise location information to provide comprehensive and coherent multi-modal explanations. All information is comprehensively presented in a diagnostic interface for use in clinical routines. An educational mode provides dataset-level explanation statistics and tools for data and model exploration to aid medical research and education. Through rigorous quantitative and qualitative evaluation of ExAID, we show the utility of multi-modal explanations for CAD-assisted scenarios even in case of wrong predictions. We believe that ExAID will provide dermatologists an effective screening tool that they both understand and trust. Moreover, it will be the basis for similar applications in other biomedical imaging fields.

Explainable Artificial Intelligence (XAI) is at the forefront of Artificial Intelligence (AI) research with a variety of techniques and libraries coming to fruition in recent years, e.g., model agnostic explanations [1, 2], counter-factual explanations [3, 4], contrastive explanations [5] and argumentation-based explanations [6, 7]. XAI methods are ubiquitous across fields of Machine Learning (ML), where the trust factor associated with applied ML is undermined due to the black-box nature of methods. Generally speaking, a ML model takes a set of inputs (features) and predicts some output; and existing works on XAI predominantly focus on understanding relations between features and output. These approaches in XAI are successful in many areas as they suggest how an output of a model might change, should we change its inputs. Thus, interventions - manipulating inputs in specific ways with the hope of reaching some desired outcome - can be provoked using existing XAI methods when they are capable of providing relatively accurate explanations [8, 9]. However, with existing XAI holding little knowledge to consequences of interventions [10], such intervention could be susceptible to error. From both a business and ethical stand-point, we must reach beyond understanding relations between features and their outputs; we also need to understand the influence that features have on one another. We believe such knowledge holds the key to deeper understanding of model behaviours and identification of suitable interventions.

Explainable artificial intelligence and interpretable machine learning are research fields growing in importance. Yet, the underlying concepts remain somewhat elusive and lack generally agreed definitions. While recent inspiration from social sciences has refocused the work on needs and expectations of human recipients, the field still misses a concrete conceptualisation. We take steps towards addressing this challenge by reviewing the philosophical and social foundations of human explainability, which we then translate into the technological realm. In particular, we scrutinise the notion of algorithmic black boxes and the spectrum of understanding determined by explanatory processes and explainees' background knowledge. This approach allows us to define explainability as (logical) reasoning applied to transparent insights (into black boxes) interpreted under certain background knowledge - a process that engenders understanding in explainees. We then employ this conceptualisation to revisit the much disputed trade-off between transparency and predictive power and its implications for ante-hoc and post-hoc explainers as well as fairness and accountability engendered by explainability. We furthermore discuss components of the machine learning workflow that may be in need of interpretability, building on a range of ideas from human-centred explainability, with a focus on explainees, contrastive statements and explanatory processes. Our discussion reconciles and complements current research to help better navigate open questions - rather than attempting to address any individual issue - thus laying a solid foundation for a grounded discussion and future progress of explainable artificial intelligence and interpretable machine learning. We conclude with a summary of our findings, revisiting the human-centred explanatory process needed to achieve the desired level of algorithmic transparency.

Machine learning models need to provide contrastive explanations, since people often seek to understand why a puzzling prediction occurred instead of some expected outcome. Current contrastive explanations are rudimentary comparisons between examples or raw features, which remain difficult to interpret, since they lack semantic meaning. We argue that explanations must be more relatable to other concepts, hypotheticals, and associations. Inspired by the perceptual process from cognitive psychology, we propose the XAI Perceptual Processing Framework and RexNet model for relatable explainable AI with Contrastive Saliency, Counterfactual Synthetic, and Contrastive Cues explanations. We investigated the application of vocal emotion recognition, and implemented a modular multi-task deep neural network to predict and explain emotions from speech. From think-aloud and controlled studies, we found that counterfactual explanations were useful and further enhanced with semantic cues, but not saliency explanations. This work provides insights into providing and evaluating relatable contrastive explainable AI for perception applications.