相关论文: What are human values, and how do we align AI to t…

Given that Artificial Intelligence (AI) increasingly permeates our lives, it is critical that we systematically align AI objectives with the goals and values of humans. The human-AI alignment problem stems from the impracticality of…

Ensuring that Large Language Models (LLMs) align with the diverse and evolving human values across different regions and cultures remains a critical challenge in AI ethics. Current alignment approaches often yield superficial conformity…

In high-stakes AI-supported decisions, considerations are not purely technical but involve moral judgments about fairness, responsibility, and harm. While prior research has focused mainly on functional or behavioral alignment, this paper…

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…

This paper examines the challenges associated with achieving life-long superalignment in AI systems, particularly large language models (LLMs). Superalignment is a theoretical framework that aspires to ensure that superintelligent AI…

As large language models (LLMs) are increasingly deployed in consequential decision-making contexts, systematically assessing their ethical reasoning capabilities becomes a critical imperative. This paper introduces the Priorities in…

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…

Aligning AI agents with human values is challenging due to diverse and subjective notions of values. Standard alignment methods often aggregate crowd feedback, which can result in the suppression of unique or minority preferences. We…

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…

We argue that enabling human-AI dialogue, purposed to support joint reasoning (i.e., 'inquiry'), is important for ensuring that AI decision making is aligned with human values and preferences. In particular, we point to logic-based models…

We evaluate the moral alignment of LLMs with human preferences in multilingual trolley problems. Building on the Moral Machine experiment, which captures over 40 million human judgments across 200+ countries, we develop a cross-lingual…

Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values. We argue that before we can even attempt to align values, it is…

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…

Alignment with human preferences is an important evaluation aspect of LLMs, requiring them to be helpful, honest, safe, and to precisely follow human instructions. Evaluating large language models' (LLMs) alignment typically involves…

Conversational human-likeness plays a central role in human-AI interaction, yet it has remained difficult to define, measure, and optimize. As a result, improvements in human-like behavior are largely driven by scale or broad supervised…

principles that should govern autonomous AI systems. It essentially states that a system's goals and behaviour should be aligned with human values. But how to ensure value alignment? In this paper we first provide a formal model to…

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…

Increasing interest in ensuring the safety of next-generation Artificial Intelligence (AI) systems calls for novel approaches to embedding morality into autonomous agents. This goal differs qualitatively from traditional task-specific AI…

People increasingly rely on Large Language Models (LLMs) for moral advice, which may influence humans' decisions. Yet, little is known about how closely LLMs align with human moral judgments. To address this, we introduce the Moral Dilemma…

In the diverse array of work investigating the nature of human values from psychology, philosophy and social sciences, there is a clear consensus that values guide behaviour. More recently, a recognition that values provide a means to…