Many high-performance models suffer from a lack of interpretability. There has been an increasing influx of work on explainable artificial intelligence (XAI) in order to disentangle what is meant and expected by XAI. Nevertheless, there is no general consensus on how to produce and judge explanations. In this paper, we discuss why techniques integrating connectionist and symbolic paradigms are the most efficient solutions to produce explanations for non-technical users and we propose a reasoning model, based on definitions by Doran et al. [2017] (arXiv:1710.00794) to explain a neural network's decision. We use this explanation in order to correct bias in the network's decision rationale. We accompany this model with an example of its potential use, based on the image captioning method in Burns et al. [2018] (arXiv:1803.09797).

We present a new explainable AI (XAI) framework aimed at increasing justified human trust and reliance in the AI machine through explanations. We pose explanation as an iterative communication process, i.e. dialog, between the machine and human user. More concretely, the machine generates sequence of explanations in a dialog which takes into account three important aspects at each dialog turn: (a) human's intention (or curiosity); (b) human's understanding of the machine; and (c) machine's understanding of the human user. To do this, we use Theory of Mind (ToM) which helps us in explicitly modeling human's intention, machine's mind as inferred by the human as well as human's mind as inferred by the machine. In other words, these explicit mental representations in ToM are incorporated to learn an optimal explanation policy that takes into account human's perception and beliefs. Furthermore, we also show that ToM facilitates in quantitatively measuring justified human trust in the machine by comparing all the three mental representations. We applied our framework to three visual recognition tasks, namely, image classification, action recognition, and human body pose estimation. We argue that our ToM based explanations are practical and more natural for both expert and non-expert users to understand the internal workings of complex machine learning models. To the best of our knowledge, this is the first work to derive explanations using ToM. Extensive human study experiments verify our hypotheses, showing that the proposed explanations significantly outperform the state-of-the-art XAI methods in terms of all the standard quantitative and qualitative XAI evaluation metrics including human trust, reliance, and explanation satisfaction.

From marketing to politics, exploitation of incomplete information through selective communication of arguments is ubiquitous. In this work, we focus on development of an argumentation-theoretic model for manipulable multi-agent argumentation, where each agent may transmit deceptive information to others for tactical motives. In particular, we study characterisation of epistemic states, and their roles in deception/honesty detection and (mis)trust-building. To this end, we propose the use of intra-agent preferences to handle deception/honesty detection and inter-agent preferences to determine which agent(s) to believe in more. We show how deception/honesty in an argumentation of an agent, if detected, would alter the agent's perceived trustworthiness, and how that may affect their judgement as to which arguments should be acceptable. 1 Introduction To adequately characterise multi-agent argumentation, it is important to model what an agent sees of other agents' argumentations ( Epistemic Aspect). It is also important to model how agents interact with others ( Agent-to-Agent Interaction). These two factors determine dynamics of multi-agent argumentation, and are thus central to: argumentation-based negotiations (Cf.

As artificial intelligence and machine learning algorithms make further inroads into society, calls are increasing from multiple stakeholders for these algorithms to explain their outputs. At the same time, these stakeholders, whether they be affected citizens, government regulators, domain experts, or system developers, present different requirements for explanations. Toward addressing these needs, we introduce AI Explainability 360 (http://aix360.mybluemix.net/), an open-source software toolkit featuring eight diverse and state-of-the-art explainability methods and two evaluation metrics. Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of explanation methods, not only those in the toolkit but also in the broader literature on explainability. For data scientists and other users of the toolkit, we have implemented an extensible software architecture that organizes methods according to their place in the AI modeling pipeline. We also discuss enhancements to bring research innovations closer to consumers of explanations, ranging from simplified, more accessible versions of algorithms, to tutorials and an interactive web demo to introduce AI explainability to different audiences and application domains. Together, our toolkit and taxonomy can help identify gaps where more explainability methods are needed and provide a platform to incorporate them as they are developed.

The development of "intelligent" systems that can take decisions and perform autonomously might lead to faster and more consistent decisions. A limiting factor for a broader adoption of AI technology is the inherent risks that come with giving up human control and oversight to "intelligent" machines. Forsensitive tasks involving critical infrastructures and affecting human well-being or health, it is crucial to limit the possibility of improper, non-robust and unsafe decisions and actions. Before deploying an AI system, we see a strong need to validate its behavior, and thus establish guarantees that it will continue to perform as expected when deployed in a real-world environment. In pursuit of that objective, ways for humans to verify the agreement between the AI decision structure and their own ground-truth knowledge have been explored.

This paper studies a fundamental mechanism of how to detect a conflict between arguments given sentiments regarding acceptability of the arguments. We introduce a concept of the inverse problem of the abstract argumentation to tackle the problem. Given noisy sets of acceptable arguments, it aims to find attack relations explaining the sets well in terms of acceptability semantics. It is the inverse of the direct problem corresponding to the traditional problem of the abstract argumentation that focuses on finding sets of acceptable arguments in terms of the semantics given an attack relation between the arguments. We give a probabilistic model handling both of the problems in a way that is faithful to the acceptability semantics. From a theoretical point of view, we show that a solution to both the direct and inverse problems is a special case of the probabilistic inference on the model. We discuss that the model provides a natural extension of the semantics to cope with uncertain attack relations distributed probabilistically. From en empirical point of view, we argue that it reasonably predicts individuals sentiments regarding acceptability of arguments. This paper contributes to lay the foundation for making acceptability semantics data-driven and to provide a way to tackle the knowledge acquisition bottleneck.

Algorithmic systems (such as those deciding mortgage applications, or sentencing decisions) can be very difficult to understand, for experts as well as the general public. The EU General Data Protection Regulation (GDPR) has sparked much discussion about the "right to explanation" for the algorithm-supported decisions made about us in our everyday lives. While there's an obvious need for transparency in the automated decisions that are increasingly being made in areas like policing, education, healthcare and recruitment, explaining how these complex algorithmic decision-making systems arrive at any particular decision is a technically challenging problem--to put it mildly. In their article "Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR" which is forthcoming in the Harvard Journal of Law & Technology, Sandra Wachter, Brent Mittelstadt, and Chris Russell present the concept of "unconditional counterfactual explanations" as a novel type of explanation of automated decisions that could address many of these challenges. Counterfactual explanations describe the minimum conditions that would have led to an alternative decision (e.g. a bank loan being approved), without the need to describe the full logic of the algorithm.

Artificial Intelligence offers a lot of advantages for organisations by creating better and more efficient organisations, improving customer services with conversational AI and reducing a wide variety of risks in different industries. Although we are only at the beginning of the AI revolution that is upon us, we can already see that artificial intelligence will have a profound effect on our lives. As a result, AI governance and Explainable AI are becoming increasingly important, if we want to reap the benefits of artificial intelligence. First of all, it is important to distinguish the difference between algorithms and AI. Algorithms are a set of (complex) instructions or rules that a computer needs to follow when solving a certain problem.

European Law now requires AI to be explainable in the context of adverse decisions affecting European Union (EU) citizens. At the same time, it is expected that there will be increasing instances of AI failure as it operates on imperfect data. This paper puts forward a neurally-inspired framework called decision stacks that can provide for a way forward in research aimed at developing explainable AI. Leveraging findings from memory systems in biological brains, the decision stack framework operationalizes the definition of explainability and then proposes a test that can potentially reveal how a given AI decision came to its conclusion.

Within AI, several sub-fields are particularly relevant to - and benefit from - studies of argumentation. These include decision support, knowledge representation, nonmonotonic reasoning, and multiagent systems. Moreover, computational argumentation provides a formal investigation of problems that have been studied informally only by philosophers, and which consequently allow for the development of computational tools for argumentation, see (Atkinson et al., 2017). Since its invention by Dung (1995), abstract argumentation based on argumentation frameworks (AFs) has become a key concept for the field. In AFs, argumentation scenarios are modeled as simple directed graphs, where the vertices represent arguments and each edge corresponds to an attack between two arguments. Besides its simplicity, there are several reasons for the success story of this concept: First, a multitude of semantics (Baroni et al., 2011, 2018) allows for tight coupling of argumentation with existing formalisms from the areas of knowledge representation and logic programming; indeed, one of the main motivations of Dung's work (Dung, 1995) was to give a uniform representation of several nonmonotonic formalisms including Reiter's Default Logic, Pollock's Defeasible Logic, and Logic Programming (LP) with default negation; the latter lead to a series of works that investigated the relationship between different LP semantics and different AF semantics, see e.g.