Related papers: Strategic Alignment Patterns in National AI Polici…
Data visualizations are powerful tools for communicating patterns in quantitative data. Yet understanding any data visualization is no small feat -- succeeding requires jointly making sense of visual, numerical, and linguistic inputs…
When searching for a target within an image our brain can adopt different strategies, but which one does it choose? This question can be answered by tracking the motion of the eye while it executes the task. Following many individuals…
The deployment of AI systems faces three critical governance challenges that current frameworks fail to adequately address. First, organizations struggle with inadequate risk assessment at the use case level, exemplified by the Humana class…
The prevailing methodologies for visualizing AI risks have focused on technical issues such as data biases and model inaccuracies, often overlooking broader societal risks like job loss and surveillance. Moreover, these visualizations are…
General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that models fail on edge cases; it is that current evaluation makes…
This paper proposes a rigorous framework to examine the two-way relationship between artificial intelligence (AI), human cognition, problem-solving, and cultural adaptation across academic and business settings. It addresses a key gap by…
We consider that existing approaches to AI "safety" and "alignment" may not be using the most effective tools, teams, or approaches. We suggest that an alternative and better approach to the problem may be to treat alignment as a social…
The critical inquiry pervading the realm of Philosophy, and perhaps extending its influence across all Humanities disciplines, revolves around the intricacies of morality and normativity. Surprisingly, in recent years, this thematic thread…
Capability planning problems are pervasive throughout many areas of human interest with prominent examples found in defense and security. Planning provides a unique context for optimization that has not been explored in great detail and…
The beneficial effects of treatments vary across individuals in most studies. Treatment heterogeneity motivates practitioners to search for the optimal policy based on personal characteristics. A long-standing common practice in policy…
The Aiming for AI Interoperability report investigates the ongoing challenge of achieving regulatory and technical AI interoperability as national and global AI governance efforts are proliferating. Here, technical interoperability is the…
In high-stakes AI-supported decisions, considerations are not purely technical but involve moral judgments about fairness, responsibility, and harm. While prior research has focused mainly on functional or behavioral alignment, this paper…
This paper examines the use of scientometric overlay mapping as a tool of 'strategic intelligence' to aid the governance of emerging technologies. We develop an integrative synthesis of different overlay mapping techniques and associated…
As artificial intelligence (AI) becomes deeply integrated into critical infrastructures and everyday life, ensuring its safe deployment is one of humanity's most urgent challenges. Current AI models prioritize task optimization over safety,…
AI companies increasingly develop and deploy privacy-enhancing technologies, bias-constraining measures, evaluation frameworks, and alignment techniques -- framing them as addressing concerns related to data privacy, algorithmic fairness,…
In AI alignment, extensive latitude must be granted to annotators, either human or algorithmic, to judge which model outputs are `better' or `safer.' We refer to this latitude as alignment discretion. Such discretion remains largely…
In recent years, various methods and benchmarks have been proposed to empirically evaluate the alignment of artificial neural networks to human neural and behavioral data. But how aligned are different alignment metrics? To answer this…
Large language models (LLMs) are increasingly used in human-AI interaction research and practice, yet existing capability and safety benchmarks reveal little about the value priorities these systems express or how those priorities…
Collaborative AI systems aim at working together with humans in a shared space to achieve a common goal. This setting imposes potentially hazardous circumstances due to contacts that could harm human beings. Thus, building such systems with…
Rapid advancements in artificial intelligence (AI) have sparked growing concerns among experts, policymakers, and world leaders regarding the potential for increasingly advanced AI systems to pose existential risks. This paper reviews the…