The next question is, why do we even bother to explain something that is just a guess (but a very good one). If it works why do we even care? Actually the problem lies in us, in humans. Nowadays we don't trust anything that we cannot understand. The interesting part is that we still have trust in specialist (if it's a human specialist and not a robot), even if the error rate of a human specialist is much higher than of a specialized Artificial Neural Network.

In this paper, we explore the issue of inconsistency handling over prioritized knowledge bases (KBs), which consist of an ontology, a set of facts, and a priority relation between conflicting facts. In the database setting, a closely related scenario has been studied and led to the definition of three different notions of optimal repairs (global, Pareto, and completion) of a prioritized inconsistent database. After transferring the notions of globally-, Pareto- and completion-optimal repairs to our setting, we study the data complexity of the core reasoning tasks: query entailment under inconsistency-tolerant semantics based upon optimal repairs, existence of a unique optimal repair, and enumeration of all optimal repairs. Our results provide a nearly complete picture of the data complexity of these tasks for ontologies formulated in common DL-Lite dialects. The second contribution of our work is to clarify the relationship between optimal repairs and different notions of extensions for (set-based) argumentation frameworks. Among our results, we show that Pareto-optimal repairs correspond precisely to stable extensions (and often also to preferred extensions), and we propose a novel semantics for prioritized KBs which is inspired by grounded extensions and enjoys favourable computational properties. Our study also yields some results of independent interest concerning preference-based argumentation frameworks.

Various AI models are increasingly being considered as part of clinical decision-support tools. However, the trustworthiness of such models is rarely considered. Clinicians are more likely to use a model if they can understand and trust its predictions. Key to this is if its underlying reasoning can be explained. A Bayesian network (BN) model has the advantage that it is not a black-box and its reasoning can be explained. In this paper, we propose an incremental explanation of inference that can be applied to'hybrid' BNs, i.e. those that contain both discrete and continuous nodes. The key questions that we answer are: (1) which important evidence supports or contradicts the prediction, and (2) through which intermediate variables does the information flow. The explanation is illustrated using a real clinical case study. A small evaluation study is also conducted.

The continued improvements in the predictive accuracy of machine learning models have allowed for their widespread practical application. Yet, many decisions made with seemingly accurate models still require verification by domain experts. In addition, end-users of a model also want to understand the reasons behind specific decisions. Thus, the need for interpretability is increasingly paramount. In this paper we present an interactive visual analytics tool, ViCE, that generates counterfactual explanations to contextualize and evaluate model decisions. Each sample is assessed to identify the minimal set of changes needed to flip the model's output. These explanations aim to provide end-users with personalized actionable insights with which to understand, and possibly contest or improve, automated decisions. The results are effectively displayed in a visual interface where counterfactual explanations are highlighted and interactive methods are provided for users to explore the data and model. The functionality of the tool is demonstrated by its application to a home equity line of credit dataset.

A common workflow in data exploration is to learn a low-dimensional representation of the data, identify groups of points in that representation, and examine the differences between the groups to determine what they represent. We treat this as an interpretable machine learning problem by leveraging the model that learned the low-dimensional representation to help identify the key differences between the groups. To solve this problem, we introduce a new type of explanation, a Global Counterfactual Explanation (GCE), and our algorithm, Transitive Global Translations (TGT), for computing GCEs. TGT identifies the differences between each pair of groups using compressed sensing but constrains those pairwise differences to be consistent among all of the groups. Empirically, we demonstrate that TGT is able to identify explanations that accurately explain the model while being relatively sparse, and that these explanations match real patterns in the data.

This paper raises three questions regarding the attribution of beliefs, desires, and intentions to robots. The first one is whether humans in fact engage in robot mindreading. If they do, this raises a second question: does robot mindreading foster trust towards robots? Both of these questions are empirical, and I show that the available evidence is insufficient to answer them. Now, if we assume that the answer to both questions is affirmative, a third and more important question arises: should developers and engineers promote robot mindreading in view of their stated goal of enhancing transparency? My worry here is that by attempting to make robots more mind-readable, they are abandoning the project of understanding automatic decision processes. Features that enhance mind-readability are prone to make the factors that determine automatic decisions even more opaque than they already are. And current strategies to eliminate opacity do not enhance mind-readability. The last part of the paper discusses different ways to analyze this apparent trade-off and suggests that a possible solution must adopt tolerable degrees of opacity that depend on pragmatic factors connected to the level of trust required for the intended uses of the robot.

Given the large variety of existing logical formalisms it is of utmost importance to select the most adequate one for a specific purpose, e.g. for representing the knowledge relevant for a particular application or for using the formalism as a modeling tool for problem solving. Awareness of the nature of a logical formalism, in other words, of its fundamental intrinsic properties, is indispensable and provides the basis of an informed choice. One such intrinsic property of logic-based knowledge representation languages is the context-dependency of pieces of knowledge. In classical propositional logic, for example, there is no such context-dependence: whenever two sets of formulas are equivalent in the sense of having the same models (ordinary equivalence), then they are mutually replaceable in arbitrary contexts (strong equivalence). However, a large number of commonly used formalisms are not like classical logic which leads to a series of interesting developments.

Explainability in AI is gaining attention in the computer science community in response to the increasing success of deep learning and the important need of justifying how such systems make predictions in life-critical applications. The focus of explainability in AI has predominantly been on trying to gain insights into how machine learning systems function by exploring relationships between input data and predicted outcomes or by extracting simpler interpretable models. Through literature surveys of philosophy and social science, authors have highlighted the sharp difference between these generated explanations and human-made explanations and claimed that current explanations in AI do not take into account the complexity of human interaction to allow for effective information passing to not-expert users. In this paper we instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented. This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations. We illustrate how we can utilize this framework through two very different examples: an artificial neural network and a Prolog solver and we provide a possible implementation for both examples.

With a typical machine learning model, the traditional correlation of feature importance analysis often has limited value. In a data scientist's toolkit, are there reliable, systematic, model agnostic methods that measure feature impact accurate to the prediction? As AI gains traction with more applications, Explainable AI (XAI) is an increasingly critical component to explain with clarity and deploy with confidence. XAI technologies are becoming more mature for both machine learning and deep learning. SHAP (SHapley Additive exPlanations) is developed by Scott Lundberg at the University of Washington.

Explainability and interpretability of AI models is an essential factor affecting the safety of AI. While various explainable AI (XAI) approaches aim at mitigating the lack of transparency in deep networks, the evidence of the effectiveness of these approaches in improving usability, trust, and understanding of AI systems are still missing. We evaluate multimodal explanations in the setting of a Visual Question Answering (VQA) task, by asking users to predict the response accuracy of a VQA agent with and without explanations. We use between-subjects and within-subjects experiments to probe explanation effectiveness in terms of improving user prediction accuracy, confidence, and reliance, among other factors. The results indicate that the explanations help improve human prediction accuracy, especially in trials when the VQA system's answer is inaccurate. Furthermore, we introduce active attention, a novel method for evaluating causal attentional effects through intervention by editing attention maps. User explanation ratings are strongly correlated with human prediction accuracy and suggest the efficacy of these explanations in human-machine AI collaboration tasks.