Nowadays, Artificial Intelligence (AI) is present in all sectors of the economy. Consequently, both data-the raw material used to build AI systems- and AI have an unprecedented impact on society and there is a need to ensure that they work for its benefit. For this reason, the European Union has put data and trustworthy AI at the center of recent legislative initiatives. An important element in these regulations is transparency, understood as the provision of information to relevant stakeholders to support (...) their understanding of AI systems and data throughout their lifecycle. In recent years, an increasing number of approaches for documenting AI and datasets have emerged, both within academia and the private sector. In this work, we identify the 36 most relevant ones from more than 2200 papers related to trustworthy AI. We assess their relevance from the angle of European regulatory objectives, their coverage of AI technologies and economic sectors, and their suitability to address the specific needs of multiple stakeholders. Finally, we discuss the main documentation gaps found, including the need to better address data innovation practices (e.g. data sharing, data reuse) and large-scale algorithmic systems (e.g. those used in online platforms), and to widen the focus from algorithms and data to AI systems as a whole. (shrink)

Organisations that design and deploy artificial intelligence (AI) systems increasingly commit themselves to high-level, ethical principles. However, there still exists a gap between principles and practices in AI ethics. One major obstacle organisations face when attempting to operationalise AI Ethics is the lack of a well-defined material scope. Put differently, the question to which systems and processes AI ethics principles ought to apply remains unanswered. Of course, there exists no universally accepted definition of AI, and different systems pose different ethical (...) challenges. Nevertheless, pragmatic problem-solving demands that things should be sorted so that their grouping will promote successful actions for some specific end. In this article, we review and compare previous attempts to classify AI systems for the purpose of implementing AI governance in practice. We find that attempts to classify AI systems proposed in previous literature use one of three mental models: _the Switch_, i.e., a binary approach according to which systems either are or are not considered AI systems depending on their characteristics; _the Ladder_, i.e., a risk-based approach that classifies systems according to the ethical risks they pose; and _the Matrix_, i.e., a multi-dimensional classification of systems that take various aspects into account, such as context, input data, and decision-model. Each of these models for classifying AI systems comes with its own set of strengths and weaknesses. By conceptualising different ways of classifying AI systems into simple mental models, we hope to provide organisations that design, deploy, or regulate AI systems with the vocabulary needed to demarcate the material scope of their AI governance frameworks. (shrink)

Since the beginning of the current hype around Artificial Intelligence (AI), governments, research institutions, and the industry invited ethical, legal, and social sciences (ELS) scholars to research AI’s societal challenges from various disciplinary viewpoints and perspectives. This approach builds upon the tradition of supporting research on the societal aspects of emerging sciences and technologies, which started with the Ethical, Legal, and Social Implications (ELSI) Program in the Human Genome Project (HGP) in the early 1990s. However, although a diverse ELS research (...) community has formed since then, AI’s societal challenges came to be mostly understood under the narrow framing of ethics and disconnected from the insights and experiences of past ELS research. In this article, we make up for this gap and connect insights from past ELS researchers with current approaches to research the societal challenges of AI. We analyse and summarize the history of “ELS programs” (programs that emerged since the HGP to support ELS research in a given domain) as three distinct eras: a genomics era, a nano era, and an RRI era. Each of these eras comprises several achievements and challenges relevant to ELS programs in AI research, such as the setup of independent funding bodies, the engagement of the wider public in research practice, and the increasing importance of private actors. Based on these insights, we argue that AI research currently falls back on self-regulatory, less participatory, and industry-led approaches that trouble ELS programs’ past achievements and hinder opportunities to overcome the still-existing challenges. (shrink)

Responsible Artificial Intelligence (RAI) is a subset of the ethics associated with the use of artificial intelligence, which will only increase with the recent advent of new regulatory frameworks. However, if many firms have announced the establishment of AI governance rules, there is currently an important gap in understanding whether and why these announcements are being implemented or remain “decoupled” from operations. We assess how large global firms have so far implemented RAI, and the antecedents to RAI implementation across a (...) wide range of RAI initiatives. We find that the operationalization of RAI practices is scattered across firms, with only a fringe of companies extensively industrializing RAI. Social pressure pushes RAI design (”saying”) rather than implementation but the reverse is true for competitive pressure. AI capabilities as a bundle of data quality AI architecture, and talents are strongly associated with RAI design to scaling. (shrink)