Objective task performance, measured as development of mean number of generated aliens per round per group. In their work For Better or Worse: The Impact of Counterfactual Explanations' Directionality on User Behavior in xAI, Ulrike Kuhl, and colleagues André Artelt and Barbara Hammer, have investigated counterfactual explanations in explainable artificial intelligence. In this interview, Ulrike tells us more about their study, and highlights some of their interesting and surprising findings. Counterfactual statements are something we as humans use every day. Phrases like "If I had gotten up earlier, I would have been on time" are counterfactuals, describing a hypothetical alternative to the current, factual state. In the realm of explainable AI (xAI), counterfactuals play a pivotal role by providing accessible and intuitive insights into the decision-making processes of AI models.

We investigate a formalism for the conditions of a successful explanation of AI. We consider "success" to depend not only on what information the explanation contains, but also on what information the human explainee understands from it. Theory of mind literature discusses the folk concepts that humans use to understand and generalize behavior. We posit that folk concepts of behavior provide us with a "language" that humans understand behavior with. We use these folk concepts as a framework of social attribution by the human explainee--the information constructs that humans are likely to comprehend from explanations--by introducing a blueprint for an explanatory narrative (Figure 1) that explains AI behavior with these constructs. We then demonstrate that many XAI methods today can be mapped to folk concepts of behavior in a qualitative evaluation. This allows us to uncover their failure modes that prevent current methods from explaining successfully--i.e., the information constructs that are missing for any given XAI method, and whose inclusion can decrease the likelihood of misunderstanding AI behavior.

A common feature of non-monotonic logics is that the classical notion of equivalence does not preserve the intended meaning in light of additional information. Consequently, the term strong equivalence was coined in the literature and thoroughly investigated. In the present paper, the knowledge representation formalism under consideration is claim-augmented argumentation frameworks (CAFs) which provide a formal basis to analyze conclusion-oriented problems in argumentation by adapting a claim-focused perspective. CAFs extend Dung AFs by associating a claim to each argument representing its conclusion. In this paper, we investigate both ordinary and strong equivalence in CAFs. Thereby, we take the fact into account that one might either be interested in the actual arguments or their claims only. The former point of view naturally yields an extension of strong equivalence for AFs to the claim-based setting while the latter gives rise to a novel equivalence notion which is genuine for CAFs. We tailor, examine and compare these notions and obtain a comprehensive study of this matter for CAFs. We conclude by investigating the computational complexity of naturally arising decision problems.

An autonomous system is constructed by a manufacturer, operates in a society subject to norms and laws, and interacts with end users. All of these actors are stakeholders affected by the behavior of the autonomous system. We address the challenge of how the ethical views of such stakeholders can be integrated in the behavior of an autonomous system. We propose an ethical recommendation component called Jiminy which uses techniques from normative systems and formal argumentation to reach moral agreements among stakeholders. A Jiminy represents the ethical views of each stakeholder by using normative systems, and has three ways of resolving moral dilemmas that involve the opinions of the stakeholders. First, the Jiminy considers how the arguments of the stakeholders relate to one another, which may already resolve the dilemma. Secondly, the Jiminy combines the normative systems of the stakeholders such that the combined expertise of the stakeholders may resolve the dilemma. Thirdly, and only if these two other methods have failed, the Jiminy uses context-sensitive rules to decide which of the stakeholders take preference over the others. At the abstract level, these three methods are characterized by adding arguments, adding attacks between arguments, and revising attacks between arguments. We show how a Jiminy can be used not only for ethical reasoning and collaborative decision-making, but also to provide explanations about ethical behavior.

This paper is a contribution to the research on dynamics in assumption-based argumentation (ABA). We investigate situations where a given knowledge base undergoes certain changes. We show that two frequently investigated problems, namely enforcement of a given target atom and deciding strong equivalence of two given ABA frameworks, are intractable in general. Notably, these problems are both tractable for abstract argumentation frameworks (AFs) which admit a close correspondence to ABA by constructing semanticspreserving instances. Inspired by this observation, we search for tractable fragments for ABA frameworks by means of the instantiated AFs. We argue that the usual instantiation procedure is not suitable for the investigation of dynamic scenarios since too much information is lost when constructing the abstract framework. We thus consider an extension of AFs, called cvAFs, equipping arguments with conclusions and vulnerabilities in order to better anticipate their role after the underlying knowledge base is extended. We investigate enforcement and strong equivalence for cvAFs and present syntactic conditions to decide them. We show that the correspondence between cvAFs and ABA frameworks is close enough to capture dynamics in ABA. This yields the desired tractable fragment. We furthermore discuss consequences for the corresponding problems for logic programs.

The gut microbiome comprises a complex population of different bacterial species that are essential to human health. In recent years, scientists across several fields have found that changes in the gut microbiome can be linked to a wide variety of diseases, notably colorectal cancer (CRC). Multiple studies have revealed that a higher abundance of certain bacteria, such as Fusobacterium nucleatum and Parvimonas micra, is typically associated with CRC progression. Based on these findings, researchers have developed various artificial intelligence (AI) models to help them analyze which bacterial species are useful as CRC biomarkers. However, most of these models rely on what is known as "global explanations," meaning that they can only consider the entirety of the input data to make predictions.

Our work builds upon previous work on interpretable machine learning, and strategic machine learning. Most previous work on interpretable machine learning has focused on one of the two following types of explanations: feature-based explanations [8-10] or counterfactual explanations [12, 13, 15, 16]. Feature-based explanations help individuals understand the importance each feature has on a particular prediction, typically through local approximation, while counterfactual explanations help them understand what features would have to change for a predictive model to make a positive prediction about them. While there is not yet an agreement on what constitutes a good post-hoc explanation in the literature on interpretable machine learning, counterfactual explanations are gaining prominence because they place no constraints on the model complexity, do not require model disclosure, facilitate actionable recourse, and seem to automate compliance with the law [32]. Motivated by these desirable properties, our work focuses on counterfactual explanations and sheds light on the possibility of using explanations to increase the utility of a decision policy, uncovering a previously unexplored connection between interpretable machine learning and the nascent field of strategic machine learning.

Weaknesses: The paper's biggest omission is that it only considers decision-maker utility as opposed to social welfare/decision subjects' utility. This is significant because the model and techniques proposed are inherently extractive in the following sense: the decision-maker can and will induce the subject to pay a cost of (say) .5 in order to improve the decision-maker's utility by .01. As noted in the paper, the hope is that the improvement is worth it to both the decision-maker and the subject, but there's no guarantee that this will actually be the case. I think the experiments should at least investigate this question: does social welfare ultimately increase? Are there individuals whose utility decreases compared to the non-strategic setting?

As data-driven predictive models are increasingly used to inform decisions, it has been argued that decision makers should provide explanations that help individuals understand what would have to change for these decisions to be beneficial ones. However, there has been little discussion on the possibility that individuals may use the above counterfactual explanations to invest effort strategically and maximize their chances of receiving a beneficial decision. In this paper, our goal is to find policies and counterfactual explanations that are optimal in terms of utility in such a strategic setting. We first show that, given a pre-defined policy, the problem of finding the optimal set of counterfactual explanations is NP-hard. Then, we show that the corresponding objective is nondecreasing and satisfies submodularity and this allows a standard greedy algorithm to enjoy approximation guarantees. In addition, we further show that the problem of jointly finding both the optimal policy and set of counterfactual explanations reduces to maximizing a non-monotone submodular function. As a result, we can use a recent randomized algorithm to solve the problem, which also offers approximation guarantees. Finally, we demonstrate that, by incorporating a matroid constraint into the problem formulation, we can increase the diversity of the optimal set of counterfactual explanations and incentivize individuals across the whole spectrum of the population to self improve. Experiments on synthetic and real lending and credit card data illustrate our theoretical findings and show that the counterfactual explanations and decision policies found by our algorithms achieve higher utility than several competitive baselines.

This paper proposes and analyzes a model of strategic behavior under counterfactual explanations. In this model, a decision-maker chooses a policy and a small set of explanations that can be provided to decisions subjects who receive unfavorable decisions. In response, decision subjects follow the given explanation to improve their future outcomes. While doing so is NP Hard, the resulting formulation is shown to be submodular allowing for efficient approximations. This paper establishes an interesting connection between strategic behavior and explainability.