Related papers: A Model of Artificial Jagged Intelligence
The increasing capabilities of artificial intelligence (AI) systems make it ever more important that we interpret their internals to ensure that their intentions are aligned with human values. Yet there is reason to believe that misaligned…
Explainable AI is an emerging field providing solutions for acquiring insights into automated systems' rationale. It has been put on the AI map by suggesting ways to tackle key ethical and societal issues. Existing explanation techniques…
Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive rationale, i.e., a subset of features of an instance that…
The increasing integration of Artificial Intelligence (AI) into everyday life makes it essential to explain AI-based decision-making in a way that is understandable to all users, including those with disabilities. Accessible explanations…
In recent years, Artificial Intelligence technology has excelled in various applications across all domains and fields. However, the various algorithms in neural networks make it difficult to understand the reasons behind decisions. For…
This paper examines the assessment challenges of Responsible AI (RAI) governance efforts in globally decentralized organizations through a case study collaboration between a leading research university and a multinational enterprise. While…
This paper reviews and proposes concerns in adopting, fielding, and maintaining artificial intelligence (AI) systems. While the AI community has made rapid progress, there are challenges in certifying AI systems. Using procedures from…
In this paper we present theory and algorithms enabling classes of Artificial Intelligence (AI) systems to continuously and incrementally improve with a-priori quantifiable guarantees - or more specifically remove classification errors -…
AI (super) alignment describes the challenge of ensuring (future) AI systems behave in accordance with societal norms and goals. While a quickly evolving literature is addressing biases and inequalities, the geographic variability of…
Recent advancements in artificial intelligence (AI) have broadened the applicability of AI-generated images across various sectors, including the creative industry and design. However, their utilization in educational contexts, particularly…
This paper explores the dynamic landscape of Artificial Intelligence (AI) adoption in Africa, analysing its varied applications in addressing socio-economic challenges and fostering development. Examining the African AI ecosystem, the study…
Given that Artificial Intelligence (AI) increasingly permeates our lives, it is critical that we systematically align AI objectives with the goals and values of humans. The human-AI alignment problem stems from the impracticality of…
Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive rationale, i.e., a subset of features of an instance that…
Artificial intelligence (AI) and machine learning (ML) have made tremendous advancements in the past decades. From simple recommendation systems to more complex tumor identification systems, AI/ML systems have been utilized in a plethora of…
Artificial Intelligence (AI) has made impressive progress in recent years and represents a key technology that has a crucial impact on the economy and society. However, it is clear that AI and business models based on it can only reach…
Machine learning is now ubiquitous in societal decision-making, for example in evaluating job candidates or loan applications, and it is increasingly important to take into account how classified agents will react to the learning…
Scalable oversight protocols aim to empower evaluators to accurately verify AI models more capable than themselves. However, human evaluators are subject to biases that can lead to systematic errors. We conduct two studies examining the…
Current AI advances largely rely on scaling neural models and expanding training datasets to achieve generalization and robustness. Despite notable successes, this paradigm incurs significant environmental, economic, and ethical costs,…
Existing approaches for the design of interpretable agent behavior consider different measures of interpretability in isolation. In this paper we posit that, in the design and deployment of human-aware agents in the real world, notions of…
As artificial intelligence (AI) systems rapidly gain autonomy, the need for robust responsible AI frameworks becomes paramount. This paper investigates how organizations perceive and adapt such frameworks amidst the emerging landscape of…