相关论文: Foundational Moral Values for AI Alignment

Large language models (LLMs) are increasingly used in human-AI interaction research and practice, yet existing capability and safety benchmarks reveal little about the value priorities these systems express or how those priorities…

AI alignment is about ensuring AI systems only pursue goals and activities that are beneficial to humans. Most of the current approach to AI alignment is to learn what humans value from their behavioural data. This paper proposes a…

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…

The recent rise in popularity of large language models (LLMs) has prompted considerable concerns about their moral capabilities. Although considerable effort has been dedicated to aligning LLMs with human moral values, existing benchmarks…

Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral…

This chapter introduces a conceptual framework for qualitative risk assessment of AI, particularly in the context of the EU AI Act. The framework addresses the complexities of legal compliance and fundamental rights protection by itegrating…

This paper explores the development of an ethical guardrail framework for AI systems, emphasizing the importance of customizable guardrails that align with diverse user values and underlying ethics. We address the challenges of AI ethics by…

Because artificial intelligence (AI) increasingly mediates organizational work, fairness has become a critical governance challenge. Existing frameworks often prioritize abstract ethical principles rather than fairness-specific ones and…

Artificial intelligence (AI) alignment is fundamentally a formation problem, not only a safety problem. As Large Language Models (LLMs) increasingly mediate moral deliberation and spiritual inquiry, they do more than provide information;…

Artificial intelligence (AI) is a digital technology that will be of major importance for the development of humanity in the near future. AI has raised fundamental questions about what we should do with such systems, what the systems…

This paper presents a theoretical framework for the AI ethical resonance hypothesis, which proposes that advanced AI systems with purposefully designed cognitive structures ("ethical resonators") may emerge with the ability to identify…

There is no consensus on what constitutes human-centeredness in AI, and existing frameworks lack empirical validation. This study addresses this gap by developing a hierarchical framework of 26 attributes of human-centeredness, validated…

Algorithmic (including AI/ML) decision-making artifacts are an established and growing part of our decision-making ecosystem. They are indispensable tools for managing the flood of information needed to make effective decisions in a complex…

Minimizing negative impacts of Artificial Intelligent (AI) systems on human societies without human supervision requires them to be able to align with human values. However, most current work only addresses this issue from a technical point…

As artificial intelligence (AI) becomes deeply integrated into critical infrastructures and everyday life, ensuring its safe deployment is one of humanity's most urgent challenges. Current AI models prioritize task optimization over safety,…

Building trust in AI-based systems is deemed critical for their adoption and appropriate use. Recent research has thus attempted to evaluate how various attributes of these systems affect user trust. However, limitations regarding the…

The past decade has observed a significant advancement in AI with deep learning-based models being deployed in diverse scenarios, including safety-critical applications. As these AI systems become deeply embedded in our societal…

How can humans remain in control of artificial intelligence (AI)-based systems designed to perform tasks autonomously? Such systems are increasingly ubiquitous, creating benefits - but also undesirable situations where moral responsibility…

The more AI agents are deployed in scenarios with possibly unexpected situations, the more they need to be flexible, adaptive, and creative in achieving the goal we have given them. Thus, a certain level of freedom to choose the best path…

Responsible AI must be able to make or support decisions that consider human values and can be justified by human morals. Accommodating values and morals in responsible decision making is supported by adopting a perspective of macro ethics,…