Related papers: A theory of understanding for artificial intellige…
The ubiquity of systems using artificial intelligence or "AI" has brought increasing attention to how those systems should be regulated. The choice of how to regulate AI systems will require care. AI systems have the potential to synthesize…
Transformers trained on huge text corpora exhibit a remarkable set of capabilities, e.g., performing basic arithmetic. Given the inherent compositional nature of language, one can expect the model to learn to compose these capabilities,…
A fundamental research goal for Explainable AI (XAI) is to build models that are capable of reasoning through the generation of natural language explanations. However, the methodologies to design and evaluate explanation-based inference…
The increasing prevalence of Artificial Intelligence (AI) in safety-critical contexts such as air-traffic control leads to systems that are practical and efficient, and to some extent explainable to humans to be trusted and accepted. The…
Machine learning is making substantial progress in diverse applications. The success is mostly due to advances in deep learning. However, deep learning can make mistakes and its generalization abilities to new tasks are questionable. We ask…
In human-AI interactions, explanation is widely seen as necessary for enabling trust in AI systems. We argue that trust, however, may be a pre-requisite because explanation is sometimes impossible. We derive this result from a formalization…
We propose an ontology of building decision-making systems, with the aim of establishing Meta-Decision-Making for Artificial Intelligence (AI), improving autonomy, and creating a framework to build metrics and benchmarks upon. To this end,…
The currently dominating artificial intelligence and machine learning technology, neural networks, builds on inductive statistical learning. Neural networks of today are information processing systems void of understanding and reasoning…
As artificial intelligence is increasingly affecting all parts of society and life, there is growing recognition that human interpretability of machine learning models is important. It is often argued that accuracy or other similar…
Compositionality has traditionally been understood as a major factor in productivity of language and, more broadly, human cognition. Yet, recently, some research started to question its status, showing that artificial neural networks are…
Recent debates on artificial intelligence increasingly emphasise questions of AI consciousness and moral status, yet there remains little agreement on how such properties should be evaluated. In this paper, we argue that awareness offers a…
While large-scale models such as LLMs and diffusion models have achieved practical success, public institutions have emphasized the importance of explainability in AI. Existing methods for explaining AI, however, are not designed to provide…
Interpretability, explainability and transparency are key issues to introducing Artificial Intelligence methods in many critical domains: This is important due to ethical concerns and trust issues strongly connected to reliability,…
The rapid adoption of generative artificial intelligence (AI) in educational assessment has created new opportunities for scalable item creation, personalized feedback, and efficient formative evaluation. However, despite advances in…
The increasing incorporation of Artificial Intelligence in the form of automated systems into decision-making procedures highlights not only the importance of decision theory for automated systems but also the need for these decision…
A multitude of explainability methods and associated fidelity performance metrics have been proposed to help better understand how modern AI systems make decisions. However, much of the current work has remained theoretical -- without much…
Public attention towards explainability of artificial intelligence (AI) systems has been rising in recent years to offer methodologies for human oversight. This has translated into the proliferation of research outputs, such as from…
There is broad agreement that Artificial Intelligence (AI) systems, particularly those using Machine Learning (ML), should be able to "explain" their behavior. Unfortunately, there is little agreement as to what constitutes an…
We describe basic ideas underlying research to build and understand artificially intelligent systems: from symbolic approaches via statistical learning to interventional models relying on concepts of causality. Some of the hard open…
One of the key factors in language productivity and human cognition is the ability of systematic compositionality, which refers to understanding composed unseen examples of seen primitives. However, recent evidence reveals that the…