Abstract Explainable artificial intelligence (XAI) is a field of study that focuses on the development process of AI-based systems while making their decision-making processes understandable and transparent for users. Research already identified explainability as an emerging requirement for AI-based systems that use machine learning (ML) techniques. However, there is a notable absence of studies investigating how ML practitioners perceive the concept of explainability, the challenges they encounter, and the potential trade-offs with other quality attributes. In this study, we want to discover how practitioners define explainability for AI-based systems and what challenges they encounter in making them explainable. Furthermore, we explore how explainability interacts with other quality attributes. To this end, we conducted semi-structured interviews with 14 ML practitioners from 11 companies. Our study reveals diverse viewpoints on explainability and applied practices. Results suggest that the importance of explainability lies in enhancing transparency, refining models, and mitigating bias. Methods like SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanation (LIME) are frequently used by ML practitioners to understand how models work, while tailored approaches are typically adopted to meet the specific requirements of stakeholders. Moreover, we have discerned emerging challenges in eight categories. Issues such as effective communication with non-technical stakeholders and the absence of standardized approaches are frequently stated as recurring hurdles. We contextualize these findings in terms of requirements engineering and conclude that industry currently lacks a standardized framework to address arising explainability needs.

Artificial Intelligence (AI) is increasingly integral for doing classification and prediction tasks across various fields, including healthcare, legal systems, autonomous vehicles, and financial services [1]. As such, stakeholders such as system developers, system operators, end-users necessitate varying levels of explanations for the decisions proposed by these AI systems to enhance their trust and reliability in these systems, and use these systems in practice. The growing reliance on AI as a decision-support tool in these critical areas underscores the need for AI systems to be explainable development process and architecture, comprehensible to their users, ensuring their use is safe, responsible, and in compliance with legal standards.

Abstract Artificial intelligence (AI) permeates all fields of life, which resulted in new challenges in requirements engineering for artificial intelligence (RE4AI), e.g., the difficulty in specifying and validating requirements for AI or considering new quality requirements due to emerging ethical implications. It is currently unclear if existing RE methods are sufficient or if new ones are needed to address these challenges. Therefore, our goal is to provide a comprehensive overview of RE4AI to researchers and practitioners. What has been achieved so far, i.e., what practices are available, and what research gaps and challenges still need to be addressed? To achieve this, we conducted a systematic mapping study combining query string search and extensive snowballing. The extracted data was aggregated, and results were synthesized using thematic analysis. Our selection process led to the inclusion of 126 primary studies. Existing RE4AI research focuses mainly on requirements analysis and elicitation, with most practices applied in these areas. Furthermore, we identified requirements specification, explainability, and the gap between machine learning engineers and end-users as the most prevalent challenges, along with a few others. Additionally, we proposed seven potential research directions to address these challenges. Practitioners can use our results to identify and select suitable RE methods for working on their AI-based systems, while researchers can build on the identified gaps and research directions to push the field forward.

Artificial intelligence (AI) has a growing influence on every aspect of life. These systems need to be transparent, accountable, and explainable to be reliable and safe. Explain-ability helps to reduce the opacity of such systems and aids in gaining end-user trust in the system. Therefore, explainability can be seen as an emerging requirement for AI-based systems. A number of studies emphasize transparency and explainability of AI-based systems. However, studies on identifying stakeholders to these requirements and how to elicit and specify explainability requirements are still rare and at an early stage. This Ph.D. research aims to establish a comprehensive reference process model that can serve as a guide for practitioners to address explainability requirements concerning AI-based systems.

Abstract Heterogeneous vehicular clustering integrates multiple types of communication networks to work efficiently for various vehicular applications. One popular form of heterogeneous network is the integration of long-term evolution (LTE) and dedicated short-range communication. The heterogeneity of such a network infrastructure and the non-cooperation involved in sharing cost/data are potential problems to solve. A vehicular clustering framework is one solution to these problems, but the framework should be formally verified and validated before being deployed in the real world. To solve these issues, first, we present a heterogeneous framework, named destination and interest-aware clustering, for vehicular clustering that integrates vehicular ad hoc networks with the LTE network for improving road traffic efficiency. Then, we specify a model system of the proposed framework. The model is formally verified to evaluate its performance at the functional level using a model checking technique. To evaluate the performance of the proposed framework at the micro-level, a heterogeneous simulation environment is created by integrating state-of-the-art tools. The comparison of the simulation results with those of other known approaches shows that our proposed framework performs better.