Related papers: Goal Alignment: A Human-Aware Account of Value Ali…
AI agents -- systems that combine foundation models with reasoning, planning, memory, and tool use -- are rapidly becoming a practical interface between natural-language intent and real-world computation. This survey synthesizes the…
Existing research primarily evaluates the values of LLMs by examining their stated inclinations towards specific values. However, the "Value-Action Gap," a phenomenon rooted in environmental and social psychology, reveals discrepancies…
Alignment methods in moral domains seek to elicit moral preferences of human stakeholders and incorporate them into AI. This presupposes moral preferences as static targets, but such preferences often evolve over time. Proper alignment of…
Misalignment between model predictions and intended usage can be detrimental for the deployment of computer vision models. The issue is exacerbated when the task involves complex structured outputs, as it becomes harder to design procedures…
AI Alignment, primarily in the form of Reinforcement Learning from Human Feedback (RLHF), has been a cornerstone of the post-training phase in developing Large Language Models (LLMs). It has also been a popular research topic across various…
Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…
With increasing digitalization, Artificial Intelligence (AI) is becoming ubiquitous. AI-based systems to identify, optimize, automate, and scale solutions to complex economic and societal problems are being proposed and implemented. This…
In many real-life settings, algorithms play the role of assistants, while humans ultimately make the final decision. Often, algorithms specifically act as curators, narrowing down a wide range of options into a smaller subset that the human…
Frontier LLMs are optimised around high-resource assumptions about language, knowledge, devices, and connectivity. Whilst widely accessible, they often misfit conditions in the Global South. As a result, users must often perform additional…
This paper leverages insights from Alignment Theory (AT) research, which primarily focuses on the potential pitfalls of technical alignment in Artificial Intelligence, to critically examine the European Union's Artificial Intelligence Act…
Optimizing a given metric is a central aspect of most current AI approaches, yet overemphasizing metrics leads to manipulation, gaming, a myopic focus on short-term goals, and other unexpected negative consequences. This poses a fundamental…
Existing approaches to algorithmic fairness aim to ensure equitable outcomes if human decision-makers comply perfectly with algorithmic decisions. However, perfect compliance with the algorithm is rarely a reality or even a desirable…
Pluralistic alignment is concerned with ensuring that an AI system's objectives and behaviors are in harmony with the diversity of human values and perspectives. In this paper we study the notion of pluralistic alignment in the context of…
Artificial intelligence (AI) systems attempt to imitate human behavior. How well they do this imitation is often used to assess their utility and to attribute human-like (or artificial) intelligence to them. However, most work on AI refers…
Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are…
LLM agents are increasingly used for personalization due to their ability to communicate directly with users in natural language, integrate external knowledge bases, and negotiate with other (possibly human) agents. Especially in…
An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and…
AI systems will soon have to navigate human environments and make decisions that affect people and other AI agents whose goals and values diverge. Contractualist alignment proposes grounding those decisions in agreements that diverse…
This paper offers a roadmap for the development of scalable aligned artificial intelligence (AI) from first principle descriptions of natural intelligence. In brief, a possible path toward scalable aligned AI rests upon enabling artificial…
By comparing biological and artificial perception through the lens of illusions, we highlight critical differences in how each system constructs visual reality. Understanding these divergences can inform the development of more robust,…