Related papers: AI Alignment Breaks at the Edge
AI incident reporting requirements are emerging in regulation and policy, yet no operational criteria exist for determining when a detected AI incident warrants escalation beyond national handling to international coordination. This paper…
When should we delegate decisions to AI systems? While the value alignment literature has developed techniques for shaping AI values, less attention has been paid to how to determine, under uncertainty, when imperfect alignment is good…
As AI systems become embedded in everyday practice, value misalignment has emerged as a pressing concern. Yet, dominant alignment approaches remain model centric, treating users as passive recipients of prespecified values rather than as…
Large Language Models (LLMs) are increasingly employed in software engineering tasks such as requirements elicitation, design, and evaluation, raising critical questions regarding their alignment with human judgments on responsible AI…
AI alignment considers how we can encode AI systems in a way that is compatible with human values. The normative side of this problem asks what moral values or principles, if any, we should encode in AI. To this end, we present a framework…
In human-AI decision making, designing AI that complements human expertise has been a natural strategy to enhance human-AI collaboration, yet it often comes at the cost of decreased AI performance in areas of human strengths. This can…
Existing work on the alignment problem has focused mainly on (1) qualitative descriptions of the alignment problem; (2) attempting to align AI actions with human interests by focusing on value specification and learning; and/or (3) focusing…
Increasing rate of progress in hardware and artificial intelligence (AI) solutions is enabling a range of software systems to be deployed closer to their users, increasing application of edge software system paradigms. Edge systems support…
Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a…
Artificial intelligence (AI) has achieved remarkable breakthroughs in a wide range of fields, ranging from speech processing, image classification to drug discovery. This is driven by the explosive growth of data, advances in machine…
When organisations adopt commercial AI systems for decision support, they inherit value judgements embedded by vendors that are neither transparent nor renegotiable. The governance puzzle is not whether AI can support decisions but which…
Value alignment is essential for building AI systems that can safely and reliably interact with people. However, what a person values -- and is even capable of valuing -- depends on the concepts that they are currently using to understand…
Governments are increasingly interested in using AI to make administrative decisions cheaper, more scalable, and more consistent. But for probabilistic AI to be incorporated into public administration it must be embedded in a compliance…
Modern AI assistants are trained to follow instructions, implicitly assuming that users can clearly articulate their goals and the kind of assistance they need. Decades of behavioral research, however, show that people often engage with AI…
Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments through social interaction, current language models (LMs) are…
Edge deep learning, a paradigm change reconciling edge computing and deep learning, facilitates real-time decision making attuned to environmental factors through the close integration of computational resources and data sources. Here we…
This position paper argues that formal optimal control theory should be central to AI alignment research, offering a distinct perspective from prevailing AI safety and security approaches. While recent work in AI safety and mechanistic…
Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of…
Algorithmic (including AI/ML) decision-making artifacts are an established and growing part of our decision-making ecosystem. They are indispensable tools for managing the flood of information needed to make effective decisions in a complex…
Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…