Related papers: Co-Constructing Alignment: A Participatory Approac…
Our ability to build autonomous agents that leverage Generative AI continues to increase by the day. As builders and users of such agents it is unclear what parameters we need to align on before the agents start performing tasks on our…
Instruction-tuned Large Language Models (LLMs) are increasingly deployed as AI Assistants in firms for support in cognitive tasks. These AI assistants carry embedded perspectives which influence factors across the firm including…
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…
Mental health is a growing global concern, prompting interest in AI-driven solutions to expand access to psychosocial support. \emph{Peer support}, grounded in lived experience, offers a valuable complement to professional care. However,…
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…
Despite AI tools becoming more prevalent and applicable to a variety of workplaces, workers consistently report uncertainty about where AI applies, what problems it can help solve, and how it fits into real workflows. In other words, there…
Effective collaboration between humans and AI-based systems requires effective modeling of the human in the loop, both in terms of the mental state as well as the physical capabilities of the latter. However, these models can also open up…
Current AI training methods align models with human values only after their core capabilities have been established, resulting in models that are easily misaligned and lack deep-rooted value systems. We propose a paradigm shift from "model…
Conventional automated decision-support systems often prioritize predictive accuracy, overlooking the complexities of real-world settings where stakeholders' preferences may diverge or conflict. This can lead to outcomes that disadvantage…
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…
AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own application in concrete cases. When principles conflict, when…
As AIs rapidly advance and become more agentic, the risk they pose is governed not only by their capabilities but increasingly by their propensities, including goals and values. Tracking the emergence of goals and values has proven a…
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…
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…
As AI integrates into design practice, designers increasingly use generative AI tools to envision AI-enabled solutions, positioning AI as both design tool and design material. This dual role creates recursive value tensions distinct from…
We argue that enabling human-AI dialogue, purposed to support joint reasoning (i.e., 'inquiry'), is important for ensuring that AI decision making is aligned with human values and preferences. In particular, we point to logic-based models…
Aligning agentic AI with user intent is critical for delegating complex, socially embedded tasks, yet user preferences are often implicit, evolving, and difficult to specify upfront. We present DoubleAgents, a system for human-agent…
This paper grounds ethics in evolutionary biology, viewing moral norms as adaptive mechanisms that render cooperation fitness-viable under selection pressure. Current alignment approaches add ethics post hoc, treating it as an external…
Humans increasingly interact with artificial intelligence (AI) in decision-making. However, both AI and humans are prone to biases. While AI and human biases have been studied extensively in isolation, this paper examines their complex…
The development of ethical AI systems is currently geared toward setting objective functions that align with human objectives. However, finding such functions remains a research challenge, while in RL, setting rewards by hand is a fairly…