Related papers: Scopes of Alignment

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…

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…

Reward design plays a pivotal role in aligning large language models (LLMs) with human values, serving as the bridge between feedback signals and model optimization. This survey provides a structured organization of reward modeling and…

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…

Recent studies have demonstrated that In-Context Learning (ICL), through the use of specific demonstrations, can align Large Language Models (LLMs) with human preferences known as In-Context Alignment (ICA), indicating that models can…

AI Alignment research seeks to align human and AI goals to ensure independent actions by a machine are always ethical. This paper argues empathy is necessary for this task, despite being often neglected in favor of more deductive…

Artificial Intelligence models are becoming increasingly more powerful and accurate, supporting or even replacing humans' decision making. But with increased power and accuracy also comes higher complexity, making it hard for users to…

The popularisation of applying AI in businesses poses significant challenges relating to ethical principles, governance, and legal compliance. Although businesses have embedded AI into their day-to-day processes, they lack a unified…

Large language models improve with scale, yet feedback-based alignment still exhibits systematic deviations from intended behavior. Motivated by bounded rationality in economics and cognitive science, we view judgment as resource-limited…

This position paper states that AI Alignment in Multi-Agent Systems (MAS) should be considered a dynamic and interaction-dependent process that heavily depends on the social environment where agents are deployed, either collaborative,…

The rapid advancement of Large Language Models (LLMs) has attracted much attention to value alignment for their responsible development. However, how to define values in this context remains a largely unexplored question. Existing work…

Calls for new metrics, technical standards and governance mechanisms to guide the adoption of Artificial Intelligence (AI) in institutions and public administration are now commonplace. Yet, most research and policy efforts aimed at…

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 Helpful, Honest, and Harmless (HHH) principle is a foundational framework for aligning AI systems with human values. However, existing interpretations of the HHH principle often overlook contextual variability and conflicting…

Algorithmic fairness and explainability are foundational elements for achieving responsible AI. In this paper, we focus on their interplay, a research area that is recently receiving increasing attention. To this end, we first present two…

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…

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…

The growing adoption of foundation models calls for a paradigm shift from Data Science to Model Science. Unlike data-centric approaches, Model Science places the trained model at the core of analysis, aiming to interact, verify, explain,…

As the impact of AI on various scientific fields is increasing, it is crucial to embrace interdisciplinary knowledge to understand the impact of technology on society. The goal is to foster a research environment beyond disciplines that…

Cross-lingual alignment, the meaningful similarity of representations across languages in multilingual language models, has been an active field of research in recent years. We survey the literature of techniques to improve cross-lingual…