English
Related papers

Related papers: Full-Stack Alignment: Co-Aligning AI and Instituti…

200 papers

One of the major challenges we face with ethical AI today is developing computational systems whose reasoning and behaviour are provably aligned with human values. Human values, however, are notorious for being ambiguous, contradictory and…

Artificial Intelligence · Computer Science 2023-05-05 Nardine Osman , Mark d'Inverno

We describe cases where real recommender systems were modified in the service of various human values such as diversity, fairness, well-being, time well spent, and factual accuracy. From this we identify the current practice of values…

Information Retrieval · Computer Science 2021-07-26 Jonathan Stray , Ivan Vendrov , Jeremy Nixon , Steven Adler , Dylan Hadfield-Menell

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…

Artificial Intelligence · Computer Science 2026-04-14 Behrooz Razeghi

Motivated by mitigating potentially harmful impacts of technologies, the AI community has formulated and accepted mathematical definitions for certain pillars of accountability: e.g. privacy, fairness, and model transparency. Yet, we argue…

Machine Learning · Computer Science 2022-12-16 Teresa Datta , Daniel Nissani , Max Cembalest , Akash Khanna , Haley Massa , John P. Dickerson

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…

Human-Computer Interaction · Computer Science 2026-04-22 Anne Arzberger , Enrico Liscio , Maria Luce Lupetti , Inigo Martinez de Rituerto de Troya , Jie Yang

The growing AI field faces trust, transparency, fairness, and discrimination challenges. Despite the need for new regulations, there is a mismatch between regulatory science and AI, preventing a consistent framework. A five-layer nested…

Computers and Society · Computer Science 2024-08-27 Akshat Dubey , Zewen Yang , Georges Hattab

How can we build AI systems that can learn any set of individual human values both quickly and safely, avoiding causing harm or violating societal standards for acceptable behavior during the learning process? We explore the effects of…

Artificial Intelligence · Computer Science 2024-11-11 Andrea Wynn , Ilia Sucholutsky , Thomas L. Griffiths

Aligning AI systems with human values and the value-based preferences of various stakeholders (their value systems) is key in ethical AI. In value-aware AI systems, decision-making draws upon explicit computational representations of…

Artificial Intelligence · Computer Science 2025-07-29 Andrés Holgado-Sánchez , Holger Billhardt , Sascha Ossowski , Sara Degli-Esposti

AI Safety researchers attempting to align values of highly capable intelligent systems with those of humanity face a number of challenges including personal value extraction, multi-agent value merger and finally in-silico encoding.…

Artificial Intelligence · Computer Science 2019-01-08 Roman V. Yampolskiy

Jurisprudence, the study of how judges should properly decide cases, and alignment, the science of getting AI models to conform to human values, share a fundamental structure. These seemingly distant fields both seek to predict and shape…

Artificial Intelligence · Computer Science 2026-05-12 Nicholas Caputo

Values or principles are key elements of human society that influence people to behave and function according to an accepted standard set of social rules to maintain social order. As AI systems are becoming ubiquitous in human society, it…

Artificial Intelligence · Computer Science 2025-01-17 Md Sultan Al Nahian , Tasmia Tasrin , Spencer Frazier , Mark Riedl , Brent Harrison

The development of sophisticated artificial intelligence (AI) conversational agents based on large language models raises important questions about the relationship between human norms, values, and practices and AI design and performance.…

Computers and Society · Computer Science 2025-05-30 Rachel Katharine Sterken , James Ravi Kirkpatrick

AI policy should advance AI innovation by ensuring that its potential benefits are responsibly realized and widely shared. To achieve this, AI policymaking should place a premium on evidence: Scientific understanding and systematic analysis…

The field of AI alignment is increasingly concerned with the questions of how values are integrated into the design of generative AI systems and how their integration shapes the social consequences of AI. However, existing transparency…

Computers and Society · Computer Science 2026-02-10 Atrisha Sarkar , Isam Faik

As AI systems become more advanced, ensuring their alignment with a diverse range of individuals and societal values becomes increasingly critical. But how can we capture fundamental human values and assess the degree to which AI systems…

Human-Computer Interaction · Computer Science 2025-11-05 Hua Shen , Tiffany Knearem , Reshmi Ghosh , Yu-Ju Yang , Nicholas Clark , Tanushree Mitra , Yun Huang

With increased power and prevalence of AI systems, it is ever more critical that AI systems are designed to serve all, i.e., people with diverse values and perspectives. However, aligning models to serve pluralistic human values remains an…

Solving the AI alignment problem requires having clear, defensible values towards which AI systems can align. Currently, targets for alignment remain underspecified and do not seem to be built from a philosophically robust structure. We…

Computers and Society · Computer Science 2023-11-29 Betty Li Hou , Brian Patrick Green

Big models have greatly advanced AI's ability to understand, generate, and manipulate information and content, enabling numerous applications. However, as these models become increasingly integrated into everyday life, their inherent…

Computers and Society · Computer Science 2023-10-27 Xiaoyuan Yi , Jing Yao , Xiting Wang , Xing Xie

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

General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that models fail on edge cases; it is that current evaluation makes…

Computation and Language · Computer Science 2026-05-19 Han Bao , Yue Huang , Xiaoda Wang , Zheyuan Zhang , Yujun Zhou , Carl Yang , Xiangliang Zhang , Yanfang Ye