English
Related papers

Related papers: Value alignment: a formal approach

200 papers

We consider the challenge of AI value alignment with multiple individuals that have different reward functions and optimal policies in an underlying Markov decision process. We formalize this problem as one of policy aggregation, where the…

Artificial Intelligence · Computer Science 2024-11-07 Parand A. Alamdari , Soroush Ebadian , Ariel D. Procaccia

We are introducing Aligned, a platform for global governance and alignment of frontier models, and eventually superintelligence. While previous efforts at the major AI labs have attempted to gather inputs for alignment, these are often…

Computers and Society · Computer Science 2023-11-16 Ethan Shaotran , Ido Pesok , Sam Jones , Emi Liu

As artificial intelligence scales, the concepts of alignment, agency, and autonomy have become central to AI safety, governance, and control. However, even in human contexts, these terms lack universal definitions, varying across…

Computers and Society · Computer Science 2025-03-11 Krti Tallam

As intelligent systems are increasingly making decisions that directly affect society, perhaps the most important upcoming research direction in AI is to rethink the ethical implications of their actions. Means are needed to integrate…

Artificial Intelligence · Computer Science 2017-06-09 Virginia Dignum

A crucial consideration when developing and deploying Large Language Models (LLMs) is the human values to which these models are aligned. In the constitutional framework of alignment models are aligned to a set of principles (the…

Machine Learning · Computer Science 2026-01-27 Henry Bell , Lara Neubauer da Costa Schertel , Bochu Ding , Brandon Fain

This paper presents an extended version of the SPADE platform, which aims to empower intelligent agent systems with normative reasoning and value alignment capabilities. Normative reasoning involves evaluating social norms and their impact…

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…

The AI alignment problem, which focusses on ensuring that artificial intelligence (AI), including AGI and ASI, systems act according to human values, presents profound challenges. With the progression from narrow AI to Artificial General…

Artificial Intelligence · Computer Science 2025-07-25 Alberto Hernández-Espinosa , Felipe S. Abrahão , Olaf Witkowski , Hector Zenil

As AI systems advance in capabilities, measuring their safety and alignment to human values is becoming paramount. A fast-growing field of AI research is devoted to developing such assessments. However, most current advances therein may be…

Computers and Society · Computer Science 2026-03-17 Max Hellrigel-Holderbaum , Edward James Young

AI safety is still largely framed as alignment: training models to follow human preferences, safety policies, and normative constraints. That framing has improved the behavior of modern language models, but aligned behavior does not by…

Artificial Intelligence · Computer Science 2026-05-27 Yige Li , Yunhao Feng , Jun Sun

Current AI alignment paradigms rely on behavioral correction: external supervisors (e.g., RLHF) observe outputs, judge against preferences, and adjust parameters. This paper argues that behavioral correction is structurally analogous to an…

Computers and Society · Computer Science 2026-04-16 Rui Chai

Benchmarks are seen as the cornerstone for measuring technical progress in Artificial Intelligence (AI) research and have been developed for a variety of tasks ranging from question answering to facial recognition. An increasingly prominent…

Computers and Society · Computer Science 2022-04-12 Travis LaCroix , Alexandra Sasha Luccioni

Autonomous agents are supposed to be able to finish tasks or achieve goals that are assigned by their users through performing a sequence of actions. Since there might exist multiple plans that an agent can follow and each plan might…

Artificial Intelligence · Computer Science 2022-04-12 Jieting Luo , Beishui Liao , Dov Gabbay

Today, AI is increasingly being used in many high-stakes decision-making applications in which fairness is an important concern. Already, there are many examples of AI being biased and making questionable and unfair decisions. The AI…

Artificial Intelligence · Computer Science 2020-02-06 Yunfeng Zhang , Rachel K. E. Bellamy , Kush R. Varshney

How AI models should deal with political topics has been discussed, but it remains challenging and requires better governance. This paper examines the governance of large language models through individual and collective deliberation,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Tanusree Sharma , Yujin Potter , Zachary Kilhoffer , Yun Huang , Dawn Song , Yang Wang

Does AI understand human values? While this remains an open philosophical question, we take a pragmatic stance by introducing VAPT, the Value-Alignment Perception Toolkit, for studying how LLMs reflect people's values and how people judge…

Human-Computer Interaction · Computer Science 2026-04-15 Bhada Yun , Renn Su , April Yi Wang

Agentic artificial intelligence systems are autonomous technologies capable of pursuing complex goals with minimal human oversight and are rapidly emerging as the next frontier in AI. While these systems promise major gains in productivity,…

Computers and Society · Computer Science 2026-01-13 Theodore Roberts , Bahram Zarrin

Artificial intelligence (AI) is advancing at a pace that raises urgent questions about how to align machine decision-making with human moral values. This working paper investigates how leading AI systems prioritize moral outcomes and what…

Artificial Intelligence · Computer Science 2025-09-15 Eoin O'Doherty , Nicole Weinrauch , Andrew Talone , Uri Klempner , Xiaoyuan Yi , Xing Xie , Yi Zeng

This position paper argues that effectively "democratizing AI" requires democratic governance and alignment of AI, and that this is particularly valuable for decisions with systemic societal impacts. Initial steps -- such as Meta's…

Alignment in artificial intelligence pursues the consistency between model responses and human preferences as well as values. In practice, the multifaceted nature of human preferences inadvertently introduces what is known as the "alignment…

Computation and Language · Computer Science 2024-10-14 Yiju Guo , Ganqu Cui , Lifan Yuan , Ning Ding , Zexu Sun , Bowen Sun , Huimin Chen , Ruobing Xie , Jie Zhou , Yankai Lin , Zhiyuan Liu , Maosong Sun