Related papers: AI Alignment Breaks at the Edge

The field of artificial intelligence (AI) alignment aims to investigate whether AI technologies align with human interests and values and function in a safe and ethical manner. AI alignment is particularly relevant for large language models…

Purpose: The governance of artificial iintelligence (AI) systems requires a structured approach that connects high-level regulatory principles with practical implementation. Existing frameworks lack clarity on how regulations translate into…

If AI systems match or exceed human capabilities on a wide range of tasks, it may become difficult for humans to efficiently judge their actions -- making it hard to use human feedback to steer them towards desirable traits. One proposed…

As AI systems advance in capabilities, measuring their safety and alignment to human values is becoming paramount. A fast-growing field of AI research is devoted to developing such assessments. However, most current advances therein may be…

Artificial intelligence (AI) systems are increasingly integrated into healthcare and pharmacy workflows, supporting tasks such as medication recommendations, dosage determination, and drug interaction detection. While these systems often…

The rapid advancement of artificial intelligence systems has brought the challenge of AI alignment to the forefront of research, particularly in complex decision-making and task execution. As these systems surpass human-level performance in…

In many engineering applications, processes must be followed precisely, making conformance checking between event logs and declarative process models crucial for ensuring adherence to desired behaviors. This is a critical area where…

Defining fairness in AI remains a persistent challenge, largely due to its deeply context-dependent nature and the lack of a universal definition. While numerous mathematical formulations of fairness exist, they sometimes conflict with one…

Biological and artificial information processing systems form representations of the world that they can use to categorize, reason, plan, navigate, and make decisions. How can we measure the similarity between the representations formed by…

It is widely agreed that when AI models assist decision-makers in high-stakes domains by predicting an outcome of interest, they should communicate the confidence of their predictions. However, empirical evidence suggests that…

Artificial and biological systems may evolve similar computational solutions despite fundamental differences in architecture and learning mechanisms -- a form of convergent evolution. We demonstrate this phenomenon through large-scale…

Ensuring safe and effective use of AI requires understanding and anticipating its performance on novel tasks, from advanced scientific challenges to transformed workplace activities. So far, benchmarking has guided progress in AI, but it…

We are introducing Aligned, a platform for global governance and alignment of frontier models, and eventually superintelligence. While previous efforts at the major AI labs have attempted to gather inputs for alignment, these are often…

Safety and responsibility evaluations of advanced AI models are a critical but developing field of research and practice. In the development of Google DeepMind's advanced AI models, we innovated on and applied a broad set of approaches to…

The union of Edge Computing (EC) and Artificial Intelligence (AI) has brought forward the Edge AI concept to provide intelligent solutions close to the end-user environment, for privacy preservation, low latency to real-time performance,…

This position paper argues for metacognition as a general design principle for creating more accurate, secure, and efficient AI. The metacognitive solution involves systems monitoring their own states and judiciously allocating resources…

As AI becomes more capable, we entrust it with more general and consequential tasks. The risks from failure grow more severe with increasing task scope. It is therefore important to understand how extremely capable AI models will fail: Will…

The downstream use cases, benefits, and risks of AI systems depend significantly on the access afforded to the system, and to whom. However, the downstream implications of different access styles are not well understood, making it difficult…

Automated vehicles promise to enhance transportation safety and efficiency. However, ensuring their reliability in real-world conditions remains challenging, particularly due to rare and unexpected situations known as edge cases. While…

The meteoric rise of AI, with its rapidly expanding market capitalization, presents both transformative opportunities and critical challenges. Chief among these is the urgent need for a new, unified paradigm for trustworthy evaluation, as…