Related papers: Backward Responsibility in Transition Systems Usin…
Given an unexpected change in the output metric of a large-scale system, it is important to answer why the change occurred: which inputs caused the change in metric? A key component of such an attribution question is estimating the…
As AI systems advance and integrate into society, well-designed and transparent evaluations are becoming essential tools in AI governance, informing decisions by providing evidence about system capabilities and risks. Yet there remains a…
Explanation mechanisms from the field of Counterfactual Thinking are a widely-used paradigm for Explainable Artificial Intelligence (XAI), as they follow a natural way of reasoning that humans are familiar with. However, all common…
Training advanced AI models requires large investments in computational resources, or compute. Yet, as hardware innovation reduces the price of compute and algorithmic advances make its use more efficient, the cost of training an AI model…
An important issue for many economic experiments is how the experimenter can ensure sufficient power for rejecting one or more hypotheses. Here, we apply methods developed mainly within the area of clinical trials for testing multiple…
Societal stereotypes are at the center of a myriad of responsible AI interventions targeted at reducing the generation and propagation of potentially harmful outcomes. While these efforts are much needed, they tend to be fragmented and…
In this paper, we argue that competitive pressures could incentivize AI companies to underinvest in ensuring their systems are safe, secure, and have a positive social impact. Ensuring that AI systems are developed responsibly may therefore…
Generative AI is rapidly moving from research to deployment, elevating the need for responsible development, evaluation, and governance. We conduct a PRISMA guided review of 232 studies (November 2022 - December 2025), spanning large…
The article develops a general equilibrium model where power relations are central in the determination of unemployment, profitability, and income distribution. The paper contributes to the market forces versus institutions debate by…
Algorithmic risk assessments are increasingly used to help humans make decisions in high-stakes settings, such as medicine, criminal justice and education. In each of these cases, the purpose of the risk assessment tool is to inform…
Edge Computing enables low-latency processing for real-time applications but introduces challenges in power management due to the distributed nature of edge devices and their limited energy resources. This paper proposes a stochastic…
As the deployment of Artificial Intelligence (AI) systems in high-stakes sectors - like healthcare, finance, education, justice, and infrastructure has increased - the possibility and impact of failures of these systems have significantly…
Safety evaluation for advanced AI systems assumes that behavior observed under evaluation predicts behavior in deployment. This assumption weakens for agents with situational awareness, which may exploit regime leakage, cues distinguishing…
Standard measures of effect, including the risk ratio, the odds ratio, and the risk difference, are associated with a number of well-described shortcomings, and no consensus exists about the conditions under which investigators should…
Frontier artificial intelligence (AI) systems pose increasing risks to society, making it essential for developers to provide assurances about their safety. One approach to offering such assurances is through a safety case: a structured,…
In the current era, people and society have grown increasingly reliant on artificial intelligence (AI) technologies. AI has the potential to drive us towards a future in which all of humanity flourishes. It also comes with substantial risks…
As AI-driven computing infrastructures rapidly scale, discussions around data center design often emphasize energy consumption, water and electricity usage, workload scheduling, and thermal management. However, these perspectives often…
It is curious that AI increasingly outperforms human decision makers, yet much of the public distrusts AI to make decisions affecting their lives. In this paper we explore a novel theory that may explain one reason for this. We propose that…
While the exact definition and implementation of accountability depend on the specific context, at its core accountability describes a mechanism that will make decisions transparent and often provides means to sanction "bad" decisions. As…
The potential for negative impacts of AI has rapidly become more pervasive around the world, and this has intensified a need for responsible AI governance. While many regulatory bodies endorse risk-based approaches and a multitude of risk…