Related papers: Getting aligned on representational alignment
Large language models (LLMs) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how neural networks…
With increased power and prevalence of AI systems, it is ever more critical that AI systems are designed to serve all, i.e., people with diverse values and perspectives. However, aligning models to serve pluralistic human values remains an…
Artificial neural networks (ANNs) are increasingly used as research models, but questions remain about their generalizability and representational invariance. Biological neural networks under social constraints evolved to enable…
Benefiting from the strong reasoning capabilities, Large language models (LLMs) have demonstrated remarkable performance in recommender systems. Various efforts have been made to distill knowledge from LLMs to enhance collaborative models,…
AI is a magnificent field that directly and profoundly touches on numerous disciplines ranging from philosophy, computer science, engineering, mathematics, decision and data science and economics, to cognitive science, neuroscience and…
Deep neural networks (DNNs) transform stimuli across multiple processing stages to produce representations that can be used to solve complex tasks, such as object recognition in images. However, a full understanding of how they achieve this…
Neural embedding approaches have become a staple in the fields of computer vision, natural language processing, and more recently, graph analytics. Given the pervasive nature of these algorithms, the natural question becomes how to exploit…
Explosive growth in big data technologies and artificial intelligence [AI] applications have led to increasing pervasiveness of information facets and a rapidly growing array of information representations. Information facets, such as…
This paper investigates contextual word representation models from the lens of similarity analysis. Given a collection of trained models, we measure the similarity of their internal representations and attention. Critically, these models…
Many research fields codify their findings in standard formats, often by reporting correlations between quantities of interest. But the space of all testable correlates is far larger than scientific resources can currently address, so the…
A good teacher should not only be knowledgeable, but should also be able to communicate in a way that the student understands -- to share the student's representation of the world. In this work, we introduce a new controlled experimental…
This position paper argues that safety and alignment cannot be achieved by constraining an external system: they must emerge from the co-regulatory design of the human--AI cognitive system as a whole ("AI as Part of Self"). Contemporary AI…
The study and understanding of human behaviour is relevant to computer science, artificial intelligence, neural computation, cognitive science, philosophy, psychology, and several other areas. Presupposing cognition as basis of behaviour,…
Distributed linguistic representations are powerful tools for modelling the uncertainty and complexity of preference information in linguistic decision making. To provide a comprehensive perspective on the development of distributed…
Representation learning, and interpreting learned representations, are key areas of focus in machine learning and neuroscience. Both fields generally use representations as a means to understand or improve a system's computations. In this…
Recent success in training deep neural networks have prompted active investigation into the features learned on their intermediate layers. Such research is difficult because it requires making sense of non-linear computations performed by…
Recent advances in AI research make it increasingly plausible that artificial agents with consequential real-world impact will soon operate beyond tightly controlled environments. Ensuring that these agents are not only safe but that they…
Humans rapidly learn abstract knowledge when encountering novel environments and flexibly deploy this knowledge to guide efficient and intelligent action. Can modern AI systems learn and plan in a similar way? We study this question using a…
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…
This paper grounds ethics in evolutionary biology, viewing moral norms as adaptive mechanisms that render cooperation fitness-viable under selection pressure. Current alignment approaches add ethics post hoc, treating it as an external…