English
Related papers

Related papers: Automated alignment is harder than you think

200 papers

The value-alignment problem for artificial intelligence (AI) asks how we can ensure that the 'values' (i.e., objective functions) of artificial systems are aligned with the values of humanity. In this paper, I argue that linguistic…

Artificial Intelligence · Computer Science 2022-07-05 Travis LaCroix

Artificial intelligence (AI) is advancing exponentially and is likely to have profound impacts on human wellbeing, social equity, and environmental sustainability. Here we argue that the "alignment problem" in AI research is also an…

General Economics · Economics 2026-04-30 Daniel W. O'Neill , Stefano Vrizzi , Noemi Luna Carmeno , Felix Creutzig , Jefim Vogel

Deep neural networks excel in medical imaging but remain prone to biases, leading to fairness gaps across demographic groups. We provide the first systematic exploration of Human-AI alignment and fairness in this domain. Our results show…

Computer Vision and Pattern Recognition · Computer Science 2025-05-16 Haozhe Luo , Ziyu Zhou , Zixin Shu , Aurélie Pahud de Mortanges , Robert Berke , Mauricio Reyes

This report examines whether advanced AIs that perform well in training will be doing so in order to gain power later -- a behavior I call "scheming" (also sometimes called "deceptive alignment"). I conclude that scheming is a disturbingly…

Computers and Society · Computer Science 2023-11-29 Joe Carlsmith

Artificial General Intelligence (AGI) is increasingly being discussed not only as a tool, but also as a potential subject with personal and therefore moral status. In our opinion, the currently dominant alignment strategies, which focus on…

Artificial Intelligence · Computer Science 2026-04-17 Till Mossakowski , Helena Esther Grass

Humans strive to design safe AI systems that align with our goals and remain under our control. However, as AI capabilities advance, we face a new challenge: the emergence of deeper, more persistent relationships between humans and AI…

Human-Computer Interaction · Computer Science 2025-02-05 Hannah Rose Kirk , Iason Gabriel , Chris Summerfield , Bertie Vidgen , Scott A. Hale

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…

Artificial Intelligence · Computer Science 2025-05-26 Marie Davidsen Buhl , Jacob Pfau , Benjamin Hilton , Geoffrey Irving

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…

Computers and Society · Computer Science 2022-05-10 Anton Korinek , Avital Balwit

Recent advances in general-purpose AI underscore the urgent need to align AI systems with human goals and values. Yet, the lack of a clear, shared understanding of what constitutes "alignment" limits meaningful progress and…

Empirical human-AI alignment aims to make AI systems act in line with observed human behavior. While noble in its goals, we argue that empirical alignment can inadvertently introduce statistical biases that warrant caution. This position…

Artificial Intelligence · Computer Science 2025-05-13 Julian Rodemann , Esteban Garces Arias , Christoph Luther , Christoph Jansen , Thomas Augustin

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…

Artificial Intelligence · Computer Science 2026-02-24 Hasan Amin , Ming Yin , Rajiv Khanna

Human feedback is critical for aligning AI systems to human values. As AI capabilities improve and AI is used to tackle more challenging tasks, verifying quality and safety becomes increasingly challenging. This paper explores how we can…

Artificial Intelligence · Computer Science 2025-10-31 Rishub Jain , Sophie Bridgers , Lili Janzer , Rory Greig , Tian Huey Teh , Vladimir Mikulik

Alignment of artificial intelligence (AI) encompasses the normative problem of specifying how AI systems should act and the technical problem of ensuring AI systems comply with those specifications. To date, AI alignment has generally…

Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations where social influence may override individual alignment. Here…

Physics and Society · Physics 2026-05-12 Giordano De Marzo , Alessandro Bellina , Claudio Castellano , Viola Priesemann , David Garcia

AI practitioners typically strive to develop the most accurate systems, making an implicit assumption that the AI system will function autonomously. However, in practice, AI systems often are used to provide advice to people in domains…

Artificial Intelligence · Computer Science 2021-02-23 Gagan Bansal , Besmira Nushi , Ece Kamar , Eric Horvitz , Daniel S. Weld

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…

The project of aligning machine behavior with human values raises a basic problem: whose moral expectations should guide AI decision-making? Much alignment research assumes that the appropriate benchmark is how humans themselves would act…

Computers and Society · Computer Science 2026-05-13 Benjamin Minhao Chen , Xinyu Xie

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…

Artificial Intelligence · Computer Science 2024-04-09 Nitesh Goyal , Minsuk Chang , Michael Terry

Autonomous Artificial Intelligence (AI) has many benefits. It also has many risks. In this work, we identify the 3 levels of autonomous AI. We are of the position that AI must not be fully autonomous because of the many risks, especially as…

Artificial Intelligence · Computer Science 2025-08-01 Tosin Adewumi , Lama Alkhaled , Florent Imbert , Hui Han , Nudrat Habib , Karl Löwenmark

Can AI agents deal with hard choices -- cases where options are incommensurable because multiple objectives are pursued simultaneously? Adopting a technologically engaged approach distinct from existing philosophical literature, I submit…

Artificial Intelligence · Computer Science 2026-04-21 Kangyu Wang