Related papers: Alignment as Institutional Design: From Behavioral…
LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However,…
With Artificial intelligence (AI) to aid or automate decision-making advancing rapidly, a particular concern is its fairness. In order to create reliable, safe and trustworthy systems through human-centred artificial intelligence (HCAI)…
Institutional decisions -- regulatory compliance, clinical triage, prior authorization appeal -- require a different AI architecture than general-purpose agents provide. Agent frameworks infer authority conversationally, reconstruct…
Value alignment problems arise in scenarios where the specified objectives of an AI agent don't match the true underlying objective of its users. The problem has been widely argued to be one of the central safety problems in AI.…
Recent reports of large language models (LLMs) exhibiting behaviors such as deception, threats, or blackmail are often interpreted as evidence of alignment failure or emergent malign agency. We argue that this interpretation rests on a…
This paper develops a unified framework for evaluating the optimal degree of task automation. Moving beyond binary automate-or-not assessments, we model automation intensity as a continuous choice in which firms minimize costs by selecting…
As artificial intelligence (AI) becomes more powerful and widespread, the AI alignment problem - how to ensure that AI systems pursue the goals that we want them to pursue - has garnered growing attention. This article distinguishes two…
AI alignment research aims to develop techniques to ensure that AI systems do not cause harm. However, every alignment technique has failure modes, which are conditions in which there is a non-negligible chance that the technique fails to…
High-stakes applications rely on combining Artificial Intelligence (AI) and humans for responsive and reliable decision making. For example, content moderation in social media platforms often employs an AI-human pipeline to promptly remove…
Contemporary artificial intelligence research has been organized around two dominant ambitions: productivity, which treats AI systems as tools for accelerating work and economic output, and alignment, which focuses on ensuring that…
Value alignment has emerged in recent years as a basic principle to produce beneficial and mindful Artificial Intelligence systems. It mainly states that autonomous entities should behave in a way that is aligned with our human values. In…
Modern language model deployments must often balance competing objectives, for example, helpfulness versus harmlessness, cost versus accuracy, and reward versus safety. We introduce Conformal Arbitrage, a post hoc framework that learns a…
Existing AI alignment approaches assume that preferences are static, which is unrealistic: our preferences change, and may even be influenced by our interactions with AI systems themselves. To clarify the consequences of incorrectly…
The influence of Artificial Intelligence (AI), and specifically Large Language Models (LLM), on education is continuously increasing. These models are frequently used by students, giving rise to the question whether current forms of…
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…
Vertical AI firms in accounting, law, healthcare, procurement, and similar domains historically bundled workflow, domain logic, and accountability into a single application. General-purpose AI agents are now unbundling that package,…
A dialogue is successful when there is alignment between the speakers at different linguistic levels. In this work, we consider the dialogue occurring between interlocutors engaged in a collaborative learning task, where they are not only…
AI systems have found a wide range of application areas in financial services. Their involvement in broader and increasingly critical decisions has escalated the need for compliance and effective model governance. Current governance…
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…
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…