As machine learning algorithms increasingly influence crucial life decisions, such as lending or job selection, providing actionable explanations becomes paramount. These explanations must clarify the reasoning behind an AI’s decision and empower individuals to alter these outcomes. This study clarifies the concept of actionability within explainable AI (XAI) by evaluating the effectiveness of non-direct and directive counterfactual explanations. Non-directive explanations detail the changes needed for a different decision, while directive explanations provide specific actions toward achieving a desired result. Our research assesses the actionability of these explanation types by utilizing existing actionability instruments complemented by open-ended queries. Our quantitative and qualitative analyses converge on the importance of clarity, relevance, feasibility, and user-centricity in explanations, highlighting how these factors significantly influence users’ ability to understand and act upon AI-generated explanations. This study suggests enriching.

We consider the effectiveness of multiobjective counterfactual explanations (MOCEs) in helping individuals learntactics, or rules of thumb, to apply when required to select a course of action in a specific context. In this setting, a counterfactual explanation compares one course of action against another. A MOCE presents this comparison by highlighting how the two options differ across a range of objectives or metrics. We conduct a study in which participants are presented with various scenarios alongside courses of action that could be implemented in those scenarios. Counterfactual explanations, including those involving multiple objectives, are used to identify the positive and negative aspects of the provided options. Participants were then required to identify the best course of action in various contexts. Participants trained with MOCE outperformed those given no explanations in seven of eight scenarios and those given single-objective counterfactual explanations (SOCEs) in four. SOCEs gave participants an aggregated outcome (expected rewards) without breaking these into specific objectives. MOCE improved tactic learning, but participants provided with SOCE or no explanation performed better in multitactic scenarios. These findings suggest that MOCE enhances tactical decision-making, but further research is needed for multitactic integration.

In this article, we introduce and evaluate a tool for researchers and practitioners to assess the actionability of information provided to users to support algorithmic recourse. While there are clear benefits of recourse from the user’s perspective, the notion of actionability in explainable AI research remains vague, and claims of ‘actionable’ explainability techniques are based on researchers’ intuitions. Inspired by definitions and instruments for assessing actionability in other domains, we construct a seven-item tool and investigate its effectiveness through two user studies. We show that the tool discriminates actionability across explanation types and that the distinctions align with human judgments. We illustrate the impact of context on actionability assessments, suggesting that domain-specific tool adaptations may foster more human-centred algorithmic systems. This is a valuable step forward for research and practices into actionable explainability and algorithmic recourse, providing the first clear human-centred tool for assessing actionability in explainable AI.

Prior research on AI-assisted human decision-making has explored several different explainable AI (XAI) approaches. A recent paper has proposed a paradigm shift calling for hypothesis-driven XAI through a conceptual framework called evaluative AI that gives people evidence that supports or refutes hypotheses without necessarily giving a decision-aid recommendation. In this paper, we describe and evaluate an approach for hypothesis-driven XAI based on the Weight of Evidence (WoE) framework, which generates both positive and negative evidence for a given hypothesis. Through human behavioural experiments, we show that our hypothesis-driven approach increases decision accuracy and reduces reliance compared to a recommendation-driven approach and an AI-explanation-only baseline, but with a small increase in under-reliance compared to the recommendation-driven approach. Further, we show that participants used our hypothesis-driven approach in a materially different way to the two baselines.

Security Operations Centres (SOCs) play a pivotal role in defending organisations against evolving cyber threats. They function as central hubs for detecting, analysing, and responding promptly to cyber incidents with the primary objective of ensuring the confidentiality, integrity, and availability of digital assets. However, they struggle against the growing problem of alert fatigue, where the sheer volume of alerts overwhelms SOC analysts and raises the risk of overlooking critical threats. In recent times, there has been a growing call for human-AI teaming, wherein humans and AI collaborate with each other, leveraging their complementary strengths and compensating for their weaknesses. The rapid advances in AI and the growing integration of AI-enabled tools and technologies within SOCs give rise to a compelling argument for the implementation of human-AI teaming within the SOC environment. Therefore, in this article, we present our vision for human-AI teaming to address the problem of alert fatigue in the SOC. We propose the 𝒜 2 𝒞 Framework, which enables flexible and dynamic decision making by allowing seamless transitions between automated, augmented, and collaborative modes of operation. Our framework allows AI-powered automation for routine alerts, AI-driven augmentation for expedited expert decision making, and collaborative exploration for tackling complex, novel threats. By implementing and operationalising 𝒜 2 𝒞, SOCs can significantly reduce alert fatigue while empowering analysts to efficiently and effectively respond to security incidents.

Displaying confidence scores in human-AI interaction has been shown to help build trust between humans and AI systems. However, most existing research uses only the confidence score as a form of communication. As confidence scores are just another model output, users may want to understand why the algorithm is confident to determine whether to accept the confidence score. In this paper, we show that counterfactual explanations of confidence scores help study participants to better understand and better trust a machine learning model's prediction. We present two methods for understanding model confidence using counterfactual explanation: (1) based on counterfactual examples; and (2) based on visualisation of the counterfactual space. Both increase understanding and trust for study participants over a baseline of no explanation, but qualitative results show that they are used quite differently, leading to recommendations of when to use each one and directions of designing better explanations.

In this article, we show that explanations of decisions made by machine learning systems can be improved by not only explaining why a decision was made but also explaining how an individual could obtain their desired outcome. We formally define the concept of directive explanations (those that offer specific actions an individual could take to achieve their desired outcome), introduce two forms of directive explanations (directive-specific and directive-generic), and describe how these can be generated computationally. We investigate people’s preference for and perception toward directive explanations through two online studies, one quantitative and the other qualitative, each covering two domains (the credit scoring domain and the employee satisfaction domain). We find a significant preference for both forms of directive explanations compared to non-directive counterfactual explanations. However, we also find that preferences are affected by many aspects, including individual preferences and social factors. We conclude that deciding what type of explanation to provide requires information about the recipients and other contextual information. This reinforces the need for a human-centered and context-specific approach to explainable AI.

Eye gaze has the potential to provide insight into the minds of individuals, and this idea has been used in prior research to improve human goal recognition by combining human's actions and gaze. However, most existing research assumes that people are rational and honest. In adversarial scenarios, people may deliberately alter their actions and gaze, which presents a challenge to goal recognition systems. In this paper, we present new models for goal recognition under deception using a combination of gaze behaviour and observed movements of the agent. These models aim to detect when a person is deceiving by analysing their gaze patterns and use this information to adjust the goal recognition. We evaluated our models in two human-subject studies: (1) using data collected from 30 individuals playing a navigation game inspired by an existing deception study and (2) using data collected from 40 individuals playing a competitive game (Ticket To Ride). We found that one of our models (Modulated Deception Gaze+Ontic) offers promising results compared to the previous state-of-the-art model in both studies. Our work complements existing adversarial goal recognition systems by equipping these systems with the ability to tackle ambiguous gaze behaviours.

This paper presents a negotiation-based obstacle avoidance scheme for teams involved in cooperative load transportation. A decentralised behaviour-based cooperative control coordinates the team's motion. The negotiation protocol is implemented as one of the behaviours within the control scheme, and utilises explicit and local communication. We tested the cooperative control in simulation and show that the cooperative control is successful as well as scalable and robust. We also demonstrate the strength of the fuzzy logic based motion controllers in mitigating the effects of approximate team heading.