Related papers: Towards a General-Purpose Belief Maintenance Syste…
The problem of human trust in artificial intelligence is one of the most fundamental problems in applied machine learning. Our processes for evaluating AI trustworthiness have substantial ramifications for ML's impact on science, health,…
Human users increasingly communicate with large language models (LLMs), but LLMs suffer from frequent overconfidence in their output, even when its accuracy is questionable, which undermines their trustworthiness and perceived legitimacy.…
In this Chapter, I will explore the use of modeling in order to understand how Science works. I will discuss the modeling of scientific communities, providing a general, non-comprehensive overview of existing models, with a focus on the use…
As machine learning becomes more widespread and is used in more critical applications, it's important to provide explanations for these models, to prevent unintended behavior. Unfortunately, many current interpretability methods struggle…
In the age of generative AI and ubiquitous digital tools, human cognition faces a structural paradox: as external aids become more capable, internal memory systems risk atrophy. Drawing on neuroscience and cognitive psychology, this paper…
Beliefs and values are increasingly being incorporated into our AI systems through alignment processes, such as carefully curating data collection principles or regularizing the loss function used for training. However, the meta-alignment…
Natural language explanations play a fundamental role in Natural Language Inference (NLI) by revealing how premises logically entail hypotheses. Recent work has shown that the interaction of large language models (LLMs) with theorem provers…
Assessing the trustworthiness of artificial intelligence systems requires knowledge from many different disciplines. These disciplines do not necessarily share concepts between them and might use words with different meanings, or even use…
Recent reports claim that Large Language Models (LLMs) have achieved the ability to derive new science and exhibit human-level general intelligence. We argue that such claims are not rigorous scientific claims, as they do not satisfy…
A current concern in the field of Artificial Intelligence (AI) is to ensure the trustworthiness of AI systems. The development of explainability methods is one prominent way to address this, which has often resulted in the assumption that…
This paper develops a comprehensive framework for artificial intelligence systems that operate under strict epistemic constraints, moving beyond stochastic language prediction to support structured reasoning, propositional commitment, and…
This theoretical work examines 'hallucinations' in both human cognition and large language models, comparing how each system can produce perceptions or outputs that deviate from reality. Drawing on neuroscience and machine learning…
Rapid progress in Neural Machine Translation (NMT) systems over the last few years has been driven primarily towards improving translation quality, and as a secondary focus, improved robustness to input perturbations (e.g. spelling and…
The paper investigates whether and how AI systems can realize states of uncertainty. By adopting a functionalist and behavioral perspective, it examines how symbolic, connectionist and hybrid architectures make room for uncertainty. The…
The study of belief change has been an active area in philosophy and AI. In recent years two special cases of belief change, belief revision and belief update, have been studied in detail. In a companion paper, we introduce a new framework…
AI and ML models have already found many applications in critical domains, such as healthcare and criminal justice. However, fully automating such high-stakes applications can raise ethical or fairness concerns. Instead, in such cases,…
The ability to interpret the mental state of another agent based on its behavior, also called Theory of Mind (ToM), is crucial for humans in any kind of social interaction. Artificial systems, such as intelligent assistants, would also…
Traditionally, an agent's beliefs would come from what the agent can see, hear, or sense. In the modern world, beliefs are often based on the data available to the agents. In this work, we investigate a dynamic logic of such beliefs that…
AI systems are increasingly tasked to complete responsibilities with decreasing oversight. This delegation requires users to accept certain risks, typically mitigated by perceived or actual alignment of values between humans and AI, leading…
This report examines a novel risk associated with current (and projected) AI tools. Making effective decisions about future actions requires us to reason under uncertainty (RUU), and doing so is essential to many critical real world…