Related papers: Getting aligned on representational alignment
In recent years, representation learning has become the research focus of the machine learning community. Large-scale neural networks are a crucial step toward achieving general intelligence, with their success largely attributed to their…
With AI systems becoming more powerful and pervasive, there is increasing debate about keeping their actions aligned with the broader goals and needs of humanity. This multi-disciplinary and multi-stakeholder debate must resolve many…
Today's computer vision models achieve human or near-human level performance across a wide variety of vision tasks. However, their architectures, data, and learning algorithms differ in numerous ways from those that give rise to human…
There is growing evidence that independently trained AI systems come to represent the world in the same way. In other words, independently trained embeddings from text, vision, audio, and neural signals share an underlying geometry. We call…
Decision-making systems increasingly orchestrate our world: how to intervene on the algorithmic components to build fair and equitable systems is therefore a question of utmost importance; one that is substantially complicated by the…
Neuroscience and artificial intelligence (AI) both face the challenge of interpreting high-dimensional neural data, where the comparative analysis of such data is crucial for revealing shared mechanisms and differences between these complex…
Background: Value alignment in computer science research is often used to refer to the process of aligning artificial intelligence with humans, but the way the phrase is used often lacks precision. Objectives: In this paper, we conduct a…
Recent advances in AI -- including generative approaches -- have resulted in technology that can support humans in scientific discovery and forming decisions, but may also disrupt democracies and target individuals. The responsible use of…
This paper introduces function alignment, a novel theory of mind and intelligence that is both intuitively compelling and structurally grounded. It explicitly models how meaning, interpretation, and analogy emerge from interactions among…
Inner Interpretability is a promising emerging field tasked with uncovering the inner mechanisms of AI systems, though how to develop these mechanistic theories is still much debated. Moreover, recent critiques raise issues that question…
How can we build AI systems that can learn any set of individual human values both quickly and safely, avoiding causing harm or violating societal standards for acceptable behavior during the learning process? We explore the effects of…
Humans represent scenes and objects in rich feature spaces, carrying information that allows us to generalise about category memberships and abstract functions with few examples. What determines whether a neural network model generalises…
Comparing the internal representations of neural networks is a central goal in both neuroscience and machine learning. Standard alignment metrics operate on raw neural activations, implicitly assuming that similar representations produce…
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…
AI Planning, Machine Learning and Process Mining have so far developed into separate research fields. At the same time, many interesting concepts and insights have been gained at the intersection of these areas in recent years. For example,…
One of the most significant problems which inhibits further developments in the areas of Knowledge Representation and Artificial Intelligence is a problem of semantic alignment or knowledge mapping. The progress in its solution will be…
Artificial neural networks are being proposed as models of parts of the brain. The networks are compared to recordings of biological neurons, and good performance in reproducing neural responses is considered to support the model's…
In the last few years, the interest in knowledge bases has grown exponentially in both the research community and the industry due to their essential role in AI applications. Entity alignment is an important task for enriching knowledge…
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…
Inferring from inconsistency and making decisions are two problems which have always been treated separately by researchers in Artificial Intelligence. Consequently, different models have been proposed for each category. Different…