Explainable AI is the hype! But depending on the use case the AI has to be explainable. Imagine if your loan broker rejected you without proper reason and you would have to move out of your house, or if the insurance premium were to be set by a black box with no real way to know what affects the resulting premium. But what is a system that provides explainable AI? It is a system that supports their decisions with compelling arguments.

Explainable AI has attracted much research attention in recent years with feature attribution algorithms, which compute "feature importance" in predictions, becoming increasingly popular. However, there is little analysis of the validity of these algorithms as there is no "ground truth" in the existing datasets to validate their correctness. In this work, we develop a method to quantitatively evaluate the correctness of XAI algorithms by creating datasets with known explanation ground truth. To this end, we focus on the binary classification problems. String datasets are constructed using formal language derived from a grammar. A string is positive if and only if a certain property is fulfilled. Symbols serving as explanation ground truth in a positive string are part of an explanation if and only if they contributes to fulfilling the property. Two popular feature attribution explainers, Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP), are used in our experiments.We show that: (1) classification accuracy is positively correlated with explanation accuracy; (2) SHAP provides more accurate explanations than LIME; (3) explanation accuracy is negatively correlated with dataset complexity.

"So, the machine has high accuracy and explains its decisions, but we still don't have engagement with our users?" I asked seeking clarification on a rather perplexing situation. Aware of my prior work in Explainable AI (XAI) around rationale generation, a prominent tech company had just hired me to solve a unique problem. They invested significant resources to build an AI-powered cybersecurity system that aims to help analysts manage firewall configurations, especially "bloat" that happens when people forget to close open ports. Over time, these open ports accumulate and create security vulnerability. Not only did this system have commendable accuracy, it also tried to explain its decision via technical (or algorithmic) transparency. But, there was almost zero to no traction amongst its users. I think we just need better models…we need to build better rationales [natural language explanations] … guess that's why we brought you in!" the team's director chuckled as we continued the ...

An explain-able multi-attribute decision model based on argumentation.

Transparency is an essential requirement of machine learning based decision making systems that are deployed in real world. Often, transparency of a given system is achieved by providing explanations of the behaviour and predictions of the given system. Counterfactual explanations are a prominent instance of particular intuitive explanations of decision making systems. While a lot of different methods for computing counterfactual explanations exist, only very few work (apart from work from the causality domain) considers feature dependencies as well as plausibility which might limit the set of possible counterfactual explanations. In this work we enhance our previous work on convex modeling for computing counterfactual explanations by a mechanism for ensuring actionability and plausibility of the resulting counterfactual explanations.

Neural network architectures are achieving superhuman performance on an expanding range of tasks. To effectively and safely deploy these systems, their decision-making must be understandable to a wide range of stakeholders. Methods to explain AI have been proposed to answer this challenge, but a lack of theory impedes the development of systematic abstractions which are necessary for cumulative knowledge gains. We propose Bayesian Teaching as a framework for unifying explainable AI (XAI) by integrating machine learning and human learning. Bayesian Teaching formalizes explanation as a communication act of an explainer to shift the beliefs of an explainee. This formalization decomposes any XAI method into four components: (1) the inference to be explained, (2) the explanatory medium, (3) the explainee model, and (4) the explainer model. The abstraction afforded by Bayesian Teaching to decompose any XAI method elucidates the invariances among them. The decomposition of XAI systems enables modular validation, as each of the first three components listed can be tested semi-independently. This decomposition also promotes generalization through recombination of components from different XAI systems, which facilitates the generation of novel variants. These new variants need not be evaluated one by one provided that each component has been validated, leading to an exponential decrease in development time. Finally, by making the goal of explanation explicit, Bayesian Teaching helps developers to assess how suitable an XAI system is for its intended real-world use case. Thus, Bayesian Teaching provides a theoretical framework that encourages systematic, scientific investigation of XAI.

The article isn't really insightful as it simply successfully attacks a very "weak" strawman. In particular, the article successfully challenges the assumption, quoting "that we must always sacrifice some interpretability to get the most accurate model" (emphasis on "always" mine) by choosing a particular problem on a tiny dataset where there exists a very, very simple model (a heuristic rule described in a single sentence) that gives acceptable accuracy. Yes, of course, there are many such problems, some "problem domains" are almost all like that and yes, for them there's no tradeoff involved. However, the article then tries to apply the same reasoning to a different class of problems (namely, the survey about robotic surgery and vision systems) without any reasonable grounds to do. They assume, quoting the penultimate sentence, "It is possible that an interpretable model can always be constructed--we just have not been trying."

In the meantime, a wide variety of terminologies, motivations, approaches and evaluation criteria have been developed within the scope of research on explainable artificial intelligence (XAI). Many taxonomies can be found in the literature, each with a different focus, but also showing many points of overlap. In this paper, we summarize the most cited and current taxonomies in a meta-analysis in order to highlight the essential aspects of the state-of-the-art in XAI. We also present and add terminologies as well as concepts from a large number of survey articles on the topic. Last but not least, we illustrate concepts from the higher-level taxonomy with more than 50 example methods, which we categorize accordingly, thus providing a wide-ranging overview of aspects of XAI and paving the way for use case-appropriate as well as context-specific subsequent research.

In AI and law, systems that are designed for decision support should be explainable when pursuing justice. In order for these systems to be fair and responsible, they should make correct decisions and make them using a sound and transparent rationale. In this paper, we introduce a knowledge-driven method for model-agnostic rationale evaluation using dedicated test cases, similar to unit-testing in professional software development. We apply this new method in a set of machine learning experiments aimed at extracting known knowledge structures from artificial datasets from fictional and non-fictional legal settings. We show that our method allows us to analyze the rationale of black-box machine learning systems by assessing which rationale elements are learned or not. Furthermore, we show that the rationale can be adjusted using tailor-made training data based on the results of the rationale evaluation.

The field of explainable AI (XAI) has quickly become a thriving and prolific community. However, a silent, recurrent and acknowledged issue in this area is the lack of consensus regarding its terminology. In particular, each new contribution seems to rely on its own (and often intuitive) version of terms like "explanation" and "interpretation". Such disarray encumbers the consolidation of advances in the field towards the fulfillment of scientific and regulatory demands e.g., when comparing methods or establishing their compliance with respect to biases and fairness constraints. We propose a theoretical framework that not only provides concrete definitions for these terms, but it also outlines all steps necessary to produce explanations and interpretations. The framework also allows for existing contributions to be re-contextualized such that their scope can be measured, thus making them comparable to other methods. We show that this framework is compliant with desiderata on explanations, on interpretability and on evaluation metrics. We present a use-case showing how the framework can be used to compare LIME, SHAP and MDNet, establishing their advantages and shortcomings. Finally, we discuss relevant trends in XAI as well as recommendations for future work, all from the standpoint of our framework.