Related papers: Understanding the Process of Human-AI Value Alignm…
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…
If AI systems match or exceed human capabilities on a wide range of tasks, it may become difficult for humans to efficiently judge their actions -- making it hard to use human feedback to steer them towards desirable traits. One proposed…
This paper critically evaluates the attempts to align Artificial Intelligence (AI) systems, especially Large Language Models (LLMs), with human values and intentions through Reinforcement Learning from Feedback (RLxF) methods, involving…
Given that AI systems are set to play a pivotal role in future decision-making processes, their trustworthiness and reliability are of critical concern. Due to their scale and complexity, modern AI systems resist direct interpretation, and…
Humans are increasingly coming into contact with artificial intelligence and machine learning systems. Human-centered artificial intelligence is a perspective on AI and ML that algorithms must be designed with awareness that they are part…
Researchers across cognitive, neuro-, and computer sciences increasingly reference human-like artificial intelligence and neuroAI. However, the scope and use of the terms are often inconsistent. Contributed research ranges widely from…
Aligning AI systems with organizational decision-making is typically framed as a single-target problem: make the model behave like the organization. We argue this framing obscures a deeper pluralistic challenge. We rely on a decision-policy…
The increasing use of Artificial Intelligence (AI) in critical societal domains has amplified concerns about fairness, particularly regarding unequal treatment across sensitive attributes such as race, gender, and socioeconomic status.…
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…
The use of Artificial Intelligence (AI) in high-risk, decision-making scenarios presents technical, safety, and normative challenges; problems that may only be ameliorated by human oversight. However, notions of human oversight lack a…
The introduction of artificial intelligence into activities traditionally carried out by human beings produces brutal changes. This is not without consequences for human values. This paper is about designing and implementing models of…
Value-alignment in normative multi-agent systems is used to promote a certain value and to ensure the consistent behaviour of agents in autonomous intelligent systems with human values. However, the current literature is limited to the…
An increasing number of decisions regarding the daily lives of human beings are being controlled by artificial intelligence (AI) algorithms in spheres ranging from healthcare, transportation, and education to college admissions,…
High-stakes applications rely on combining Artificial Intelligence (AI) and humans for responsive and reliable decision making. For example, content moderation in social media platforms often employs an AI-human pipeline to promptly remove…
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…
As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…
Modern Artificial Intelligence (AI) systems excel at diverse tasks, from image classification to strategy games, even outperforming humans in many of these domains. After making astounding progress in language learning in the recent decade,…
While autonomous agents often surpass humans in their ability to handle vast and complex data, their potential misalignment (i.e., lack of transparency regarding their true objective) has thus far hindered their use in critical applications…
A key concern with the concept of "alignment" is the implicit question of "alignment to what?". AI systems are increasingly used across the world, yet safety alignment is often focused on homogeneous monolingual settings. Additionally,…
Artificial intelligence risks are multidimensional in nature, as the same risk scenarios may have legal, operational, and financial risk dimensions. With the emergence of new AI regulations, the state of the art of artificial intelligence…