English
Related papers

Related papers: A testable framework for AI alignment: Simulation …

200 papers

Grounded Theory (GT), a sociological research method designed to study social phenomena, is increasingly being used to investigate the human and social aspects of software engineering (SE). However, being written by and for sociologists, GT…

Software Engineering · Computer Science 2021-09-10 Rashina Hoda

Risk thresholds provide a measure of the level of risk exposure that a society or individual is willing to withstand, ultimately shaping how we determine the safety of technological systems. Against the backdrop of the Cold War, the first…

Computers and Society · Computer Science 2025-04-22 Heidy Khlaaf , Sarah Myers West

A growing body of research has explored how to support humans in making better use of AI-based decision support, including via training and onboarding. Existing research has focused on decision-making tasks where it is possible to evaluate…

Human-Computer Interaction · Computer Science 2023-08-31 Anna Kawakami , Luke Guerdan , Yanghuidi Cheng , Matthew Lee , Scott Carter , Nikos Arechiga , Kate Glazko , Haiyi Zhu , Kenneth Holstein

AI systems are increasingly tasked to complete responsibilities with decreasing oversight. This delegation requires users to accept certain risks, typically mitigated by perceived or actual alignment of values between humans and AI, leading…

Computers and Society · Computer Science 2025-01-29 Jennifer Chien , David Danks

The European Union Artificial Intelligence (EU AI) Act, which explicitly references fundamental rights and ethical principles, is a comprehensive regulatory framework for governing Artificial Intelligence (AI) systems. This study examines…

Computers and Society · Computer Science 2026-05-11 Mehmet Murat Albayrakoglu , Mehmet Nafiz Aydin

Simulation can enable the study of recommender system (RS) evolution while circumventing many of the issues of empirical longitudinal studies; simulations are comparatively easier to implement, are highly controlled, and pose no ethical…

Computers and Society · Computer Science 2021-08-02 Amy A. Winecoff , Matthew Sun , Eli Lucherini , Arvind Narayanan

We outline the principles of classical assurance for computer-based systems that pose significant risks. We then consider application of these principles to systems that employ Artificial Intelligence (AI) and Machine Learning (ML). A key…

Artificial Intelligence · Computer Science 2025-06-04 Robin Bloomfield , John Rushby

Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside training. The phenomenon was first…

Scientific theory shift in AI agents requires more than fitting equations to data. An artificial scientific agent must detect whether an existing representational framework remains transportable into a new regime, or whether its language…

Artificial Intelligence · Computer Science 2026-05-15 David N. Olivieri , Roque J. Hernández

Despite the explosive growth of AI and the technologies built upon it, predicting and inferring the sub-optimal behavior of users or human collaborators remains a critical challenge. In many cases, such behaviors are not a result of…

Artificial Intelligence · Computer Science 2025-11-18 Yifan Zhu , Sammie Katt , Samuel Kaski

Theory of Mind (ToM) refers to the ability to attribute mental states, such as beliefs, desires, intentions, and knowledge, to oneself and others, and to understand that these mental states can differ from one's own and from reality. We…

Artificial Intelligence · Computer Science 2024-03-15 Anirban Mukherjee , Hannah Hanwen Chang

While much research in artificial intelligence (AI) has focused on scaling capabilities, the accelerating pace of development makes countervailing work on producing harmless, "aligned" systems increasingly urgent. Yet research on alignment…

Artificial Intelligence · Computer Science 2025-12-12 Dani Roytburg , Beck Miller

Aligning large language models with humans is challenging due to the inherently multifaceted nature of preference feedback. While existing approaches typically frame this as a multi-objective optimization problem, they often overlook how…

Computation and Language · Computer Science 2025-06-03 Mohamad Chehade , Soumya Suvra Ghosal , Souradip Chakraborty , Avinash Reddy , Dinesh Manocha , Hao Zhu , Amrit Singh Bedi

Large language models are increasingly influencing human moral decisions, yet current approaches focus primarily on evaluating rather than actively steering their moral decisions. We formulate this as an out-of-distribution moral alignment…

Artificial Intelligence · Computer Science 2025-11-18 Zhiyu An , Wan Du

Artificial Intelligence (AI) systems are increasingly placed in positions where their decisions have real consequences, e.g., moderating online spaces, conducting research, and advising on policy. Ensuring they operate in a safe and…

Artificial Intelligence · Computer Science 2025-05-09 Joel Z. Leibo , Alexander Sasha Vezhnevets , William A. Cunningham , Sébastien Krier , Manfred Diaz , Simon Osindero

A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as capabilities improve. We argue that, even when research agents are not scheming to…

Artificial Intelligence · Computer Science 2026-05-18 Aleksandr Bowkis , Marie Davidsen Buhl , Jacob Pfau , Geoffrey Irving

We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI…

In supervisory control settings, autonomous systems are not monitored continuously. Instead, monitoring often occurs at sporadic intervals within known bounds. We study the problem of deception, where an agent pursues a private objective…

In this paper we present theory and algorithms enabling classes of Artificial Intelligence (AI) systems to continuously and incrementally improve with a-priori quantifiable guarantees - or more specifically remove classification errors -…

Machine Learning · Computer Science 2022-05-18 Ivan Y. Tyukin , Alexander N. Gorban , Alistair A. McEwan , Sepehr Meshkinfamfard , Lixin Tang

Artificial Intelligence (AI) technology epitomizes the complex challenges posed by human-made artifacts, particularly those widely integrated into society and exerting significant influence, highlighting potential benefits and their…

Artificial Intelligence · Computer Science 2025-10-06 Michael Papademas , Xenia Ziouvelou , Antonis Troumpoukis , Vangelis Karkaletsis