Mark T. Keane

Greta Warren, Mark T. Keane, Christophe Gueret et al.

Counterfactual explanations are an increasingly popular form of post hoc explanation due to their (i) applicability across problem domains, (ii) proposed legal compliance (e.g., with GDPR), and (iii) reliance on the contrastive nature of human explanation. Although counterfactual explanations are normally used to explain individual predictive-instances, we explore a novel use case in which groups of similar instances are explained in a collective fashion using ``group counterfactuals'' (e.g., to highlight a repeating pattern of illness in a group of patients). These group counterfactuals meet a human preference for coherent, broad explanations covering multiple events/instances. A novel, group-counterfactual algorithm is proposed to generate high-coverage explanations that are faithful to the to-be-explained model. This explanation strategy is also evaluated in a large, controlled user study (N=207), using objective (i.e., accuracy) and subjective (i.e., confidence, explanation satisfaction, and trust) psychological measures. The results show that group counterfactuals elicit modest but definite improvements in people's understanding of an AI system. The implications of these findings for counterfactual methods and for XAI are discussed.

Eoin Delaney, Arjun Pakrashi, Derek Greene et al.

Counterfactual explanations have emerged as a popular solution for the eXplainable AI (XAI) problem of elucidating the predictions of black-box deep-learning systems due to their psychological validity, flexibility across problem domains and proposed legal compliance. While over 100 counterfactual methods exist, claiming to generate plausible explanations akin to those preferred by people, few have actually been tested on users ($\sim7\%$). So, the psychological validity of these counterfactual algorithms for effective XAI for image data is not established. This issue is addressed here using a novel methodology that (i) gathers ground truth human-generated counterfactual explanations for misclassified images, in two user studies and, then, (ii) compares these human-generated ground-truth explanations to computationally-generated explanations for the same misclassifications. Results indicate that humans do not "minimally edit" images when generating counterfactual explanations. Instead, they make larger, "meaningful" edits that better approximate prototypes in the counterfactual class.

Saugat Aryal, Mark T. Keane

Recently, in eXplainable AI (XAI), $\textit{even if}$ explanations -- so-called semi-factuals -- have emerged as a popular strategy that explains how a predicted outcome $\textit{can remain the same}$ even when certain input-features are altered. For example, in the commonly-used banking app scenario, a semi-factual explanation could inform customers about better options, other alternatives for their successful application, by saying "$\textit{Even if}$ you asked for double the loan amount, you would still be accepted". Most semi-factuals XAI algorithms focus on finding maximal value-changes to a single key-feature that do $\textit{not}$ alter the outcome (unlike counterfactual explanations that often find minimal value-changes to several features that alter the outcome). However, no current semi-factual method explains $\textit{why}$ these extreme value-changes do not alter outcomes; for example, a more informative semi-factual could tell the customer that it is their good credit score that allows them to borrow double their requested loan. In this work, we advance a new algorithm -- the $\textit{informative semi-factuals}$ (ISF) method -- that generates more elaborated explanations supplementing semi-factuals with information about additional $\textit{hidden features}$ that influence an automated decision. Experimental results on benchmark datasets show that this ISF method computes semi-factuals that are both informative and of high-quality on key metrics. Furthermore, a user study shows that people prefer these elaborated explanations over the simpler semi-factual explanations generated by current methods.

Saugat Aryal, Mark T. Keane

Recently, counterfactuals using "if-only" explanations have become very popular in eXplainable AI (XAI), as they describe which changes to feature-inputs of a black-box AI system result in changes to a (usually negative) decision-outcome. Even more recently, semi-factuals using "even-if" explanations have gained more attention. They elucidate the feature-input changes that do not change the decision-outcome of the AI system, with a potential to suggest more beneficial recourses. Some semi-factual methods use counterfactuals to the query-instance to guide semi-factual production (so-called counterfactual-guided methods), whereas others do not (so-called counterfactual-free methods). In this work, we perform comprehensive tests of 8 semi-factual methods on 7 datasets using 5 key metrics, to determine whether counterfactual guidance is necessary to find the best semi-factuals. The results of these tests suggests not, but rather that computing other aspects of the decision space lead to better semi-factual XAI.

Susanne Gaube, Markus Langer, Tim Miller et al.

The use of Artificial Intelligence (AI) in high-risk, decision-making scenarios presents technical, safety, and normative challenges; problems that may only be ameliorated by human oversight. However, notions of human oversight lack a common foundational understanding: oversight architectures are not well defined, the roles involved remain unclear, and implementation steps are opaque. Hence, researchers and practitioners struggle to determine how to design, implement, and evaluate systems that enable effective human oversight. This paper advances a practical framework for effective human oversight of AI systems, based on a cross-disciplinary perspective that draws on insights from computer science, human-computer interaction, psychology, philosophy, and law. The core contributions are: (1) a foundational framework, with a working definition, architecture and processes for effective human oversight of AI systems; (2) an initial template for documenting oversight architectures and processes, applied to diverse domains; and (3) a synthesis of open research challenges that need to be considered in the emerging field of effective human oversight of AI systems.

Courtney Ford, Mark T. Keane

Explainable AI (XAI) methods often struggle to generate clear, interpretable outputs for users without domain expertise. We introduce Feature-Guided Neighbor Selection (FGNS), a post hoc method that enhances interpretability by selecting class-representative examples using both local and global feature importance. In a user study (N = 98) evaluating Kannada script classifications, FGNS significantly improved non-experts' ability to identify model errors while maintaining appropriate agreement with correct predictions. Participants made faster and more accurate decisions compared to those given traditional k-NN explanations. Quantitative analysis shows that FGNS selects neighbors that better reflect class characteristics rather than merely minimizing feature-space distance, leading to more consistent selection and tighter clustering around class prototypes. These results support FGNS as a step toward more human-aligned model assessment, although further work is needed to address the gap between explanation quality and perceived trust.

Mohammed Temraz, Mark T. Keane

Learning from class imbalanced datasets poses challenges for many machine learning algorithms. Many real-world domains are, by definition, class imbalanced by virtue of having a majority class that naturally has many more instances than its minority class (e.g. genuine bank transactions occur much more often than fraudulent ones). Many methods have been proposed to solve the class imbalance problem, among the most popular being oversampling techniques (such as SMOTE). These methods generate synthetic instances in the minority class, to balance the dataset, performing data augmentations that improve the performance of predictive machine learning (ML) models. In this paper we advance a novel data augmentation method (adapted from eXplainable AI), that generates synthetic, counterfactual instances in the minority class. Unlike other oversampling techniques, this method adaptively combines exist-ing instances from the dataset, using actual feature-values rather than interpolating values between instances. Several experiments using four different classifiers and 25 datasets are reported, which show that this Counterfactual Augmentation method (CFA) generates useful synthetic data points in the minority class. The experiments also show that CFA is competitive with many other oversampling methods many of which are variants of SMOTE. The basis for CFAs performance is discussed, along with the conditions under which it is likely to perform better or worse in future tests.

Eoin Delaney, Derek Greene, Mark T. Keane

Whilst an abundance of techniques have recently been proposed to generate counterfactual explanations for the predictions of opaque black-box systems, markedly less attention has been paid to exploring the uncertainty of these generated explanations. This becomes a critical issue in high-stakes scenarios, where uncertain and misleading explanations could have dire consequences (e.g., medical diagnosis and treatment planning). Moreover, it is often difficult to determine if the generated explanations are well grounded in the training data and sensitive to distributional shifts. This paper proposes several practical solutions that can be leveraged to solve these problems by establishing novel connections with other research works in explainability (e.g., trust scores) and uncertainty estimation (e.g., Monte Carlo Dropout). Two experiments demonstrate the utility of our proposed solutions.

Cathal Ryan, Christophe Guéret, Donagh Berry et al.

Mastitis is a billion dollar health problem for the modern dairy industry, with implications for antibiotic resistance. The use of AI techniques to identify the early onset of this disease, thus has significant implications for the sustainability of this agricultural sector. Current approaches to treating mastitis involve antibiotics and this practice is coming under ever increasing scrutiny. Using machine learning models to identify cows at risk of developing mastitis and applying targeted treatment regimes to only those animals promotes a more sustainable approach. Incorrect predictions from such models, however, can lead to monetary losses, unnecessary use of antibiotics, and even the premature death of animals, so it is important to generate compelling explanations for predictions to build trust with users and to better support their decision making. In this paper we demonstrate a system developed to predict mastitis infections in cows and provide explanations of these predictions using counterfactuals. We demonstrate the system and describe the engagement with farmers undertaken to build it.

Eoin Delaney, Derek Greene, Mark T. Keane

In recent years, there has been a rapidly expanding focus on explaining the predictions made by black-box AI systems that handle image and tabular data. However, considerably less attention has been paid to explaining the predictions of opaque AI systems handling time series data. In this paper, we advance a novel model-agnostic, case-based technique -- Native Guide -- that generates counterfactual explanations for time series classifiers. Given a query time series, $T_{q}$, for which a black-box classification system predicts class, $c$, a counterfactual time series explanation shows how $T_{q}$ could change, such that the system predicts an alternative class, $c'$. The proposed instance-based technique adapts existing counterfactual instances in the case-base by highlighting and modifying discriminative areas of the time series that underlie the classification. Quantitative and qualitative results from two comparative experiments indicate that Native Guide generates plausible, proximal, sparse and diverse explanations that are better than those produced by key benchmark counterfactual methods.

Courtney Ford, Eoin M. Kenny, Mark T. Keane

This paper reports two experiments (N=349) on the impact of post hoc explanations by example and error rates on peoples perceptions of a black box classifier. Both experiments show that when people are given case based explanations, from an implemented ANN CBR twin system, they perceive miss classifications to be more correct. They also show that as error rates increase above 4%, people trust the classifier less and view it as being less correct, less reasonable and less trustworthy. The implications of these results for XAI are discussed.

Eoin M. Kenny, Mark T. Keane

There is a growing concern that the recent progress made in AI, especially regarding the predictive competence of deep learning models, will be undermined by a failure to properly explain their operation and outputs. In response to this disquiet counterfactual explanations have become massively popular in eXplainable AI (XAI) due to their proposed computational psychological, and legal benefits. In contrast however, semifactuals, which are a similar way humans commonly explain their reasoning, have surprisingly received no attention. Most counterfactual methods address tabular rather than image data, partly due to the nondiscrete nature of the latter making good counterfactuals difficult to define. Additionally generating plausible looking explanations which lie on the data manifold is another issue which hampers progress. This paper advances a novel method for generating plausible counterfactuals (and semifactuals) for black box CNN classifiers doing computer vision. The present method, called PlausIble Exceptionality-based Contrastive Explanations (PIECE), modifies all exceptional features in a test image to be normal from the perspective of the counterfactual class (hence concretely defining a counterfactual). Two controlled experiments compare this method to others in the literature, showing that PIECE not only generates the most plausible counterfactuals on several measures, but also the best semifactuals.

Mark T. Keane, Barry Smyth

Recently, a groundswell of research has identified the use of counterfactual explanations as a potentially significant solution to the Explainable AI (XAI) problem. It is argued that (a) technically, these counterfactual cases can be generated by permuting problem-features until a class change is found, (b) psychologically, they are much more causally informative than factual explanations, (c) legally, they are GDPR-compliant. However, there are issues around the finding of good counterfactuals using current techniques (e.g. sparsity and plausibility). We show that many commonly-used datasets appear to have few good counterfactuals for explanation purposes. So, we propose a new case based approach for generating counterfactuals using novel ideas about the counterfactual potential and explanatory coverage of a case-base. The new technique reuses patterns of good counterfactuals, present in a case-base, to generate analogous counterfactuals that can explain new problems and their solutions. Several experiments show how this technique can improve the counterfactual potential and explanatory coverage of case-bases that were previously found wanting.

Mark T. Keane, Eoin M. Kenny

The notion of twin systems is proposed to address the eXplainable AI (XAI) problem, where an uninterpretable black-box system is mapped to a white-box 'twin' that is more interpretable. In this short paper, we overview very recent work that advances a generic solution to the XAI problem, the so called twin system approach. The most popular twinning in the literature is that between an Artificial Neural Networks (ANN ) as a black box and Case Based Reasoning (CBR) system as a white-box, where the latter acts as an interpretable proxy for the former. We outline how recent work reviving this idea has applied it to deep learning methods. Furthermore, we detail the many fruitful directions in which this work may be taken; such as, determining the most (i) accurate feature-weighting methods to be used, (ii) appropriate deployments for explanatory cases, (iii) useful cases of explanatory value to users.

Kelleher Conor, Mark T. Keane

The post-modern novel 'Wittgenstein's Mistress' by David Markson (1988) presents the reader with a very challenging non linear narrative, that itself appears to one of the novel's themes. We present a distant reading of this work designed to complement a close reading of it by David Foster Wallace (1990). Using a combination of text analysis, entity recognition and networks, we plot repetitive structures in the novel's narrative relating them to its critical analysis.

Terrence Szymanski, Claudia Orellana-Rodriguez, Mark T. Keane

We present a software tool that employs state-of-the-art natural language processing (NLP) and machine learning techniques to help newspaper editors compose effective headlines for online publication. The system identifies the most salient keywords in a news article and ranks them based on both their overall popularity and their direct relevance to the article. The system also uses a supervised regression model to identify headlines that are likely to be widely shared on social media. The user interface is designed to simplify and speed the editor's decision process on the composition of the headline. As such, the tool provides an efficient way to combine the benefits of automated predictors of engagement and search-engine optimization (SEO) with human judgments of overall headline quality.

Stephanie OToole, Mark T. Keane

What are the cognitive after-effects of making a similarity judgement? What, cognitively, is left behind and what effect might these residues have on subsequent processing? In this paper, we probe for such after-effects using a visual search task, performed after a task in which pictures of real-world objects were compared. So, target objects were first presented in a comparison task (e.g., rate the similarity of this object to another) thus, presumably, modifying some of their features before asking people to visually search for the same object in complex scenes (with distractors and camouflaged backgrounds). As visual search is known to be influenced by the features of target objects, then any after-effects of the comparison task should be revealed in subsequent visual searches. Results showed that when people previously rated an object as being high on a scale (e.g., colour similarity or general similarity) then visual search is inhibited (slower RTs and more saccades in eye-tracking) relative to an object being rated as low in the same scale. There was also some evidence that different comparison tasks (e.g., compare on colour or compare on general similarity) have differential effects on visual search.

Meadhbh Foster, Mark T. Keane

Why are some events more surprising than others? We propose that events that are more difficult to explain are those that are more surprising. The two experiments reported here test the impact of different event outcomes (Outcome-Type) and task demands (Task) on ratings of surprise for simple story scenarios. For the Outcome-Type variable, participants saw outcomes that were either known or less-known surprising outcomes for each scenario. For the Task variable, participants either answered comprehension questions or provided an explanation of the outcome. Outcome-Type reliably affected surprise judgments; known outcomes were rated as less surprising than less-known outcomes. Task also reliably affected surprise judgments; when people provided an explanation it lowered surprise judgments relative to simply answering comprehension questions. Both experiments thus provide evidence on this less-explored explanation aspect of surprise, specifically showing that ease of explanation is a key factor in determining the level of surprise experienced.

Petra Ahrweiler, Mark T. Keane

This paper advances a framework for modeling the component interactions between cognitive and social aspects of scientific creativity and technological innovation. Specifically, it aims to characterize Innovation Networks; those networks that involve the interplay of people, ideas and organizations to create new, technologically feasible, commercially-realizable products, processes and organizational structures. The tri-partite framework captures networks of ideas (Concept Level), people (Individual Level) and social structures (Social-Organizational Level) and the interactions between these levels. At the concept level, new ideas are the nodes that are created and linked, kept open for further investigation or closed if solved by actors at the individual or organizational levels. At the individual level, the nodes are actors linked by shared worldviews (based on shared professional, educational, experiential backgrounds) who are the builders of the concept level. At the social-organizational level, the nodes are organizations linked by common efforts on a given project (e.g., a company-university collaboration) that by virtue of their intellectual property or rules of governance constrain the actions of individuals (at the Individual Level) or ideas (at the Concept Level). After describing this framework and its implications we paint a number of scenarios to flesh out how it can be applied.