Related papers: Characterizing Manipulation from AI Systems
With the widespread use of AI systems and applications in our everyday lives, it is important to take fairness issues into consideration while designing and engineering these types of systems. Such systems can be used in many sensitive…
The ability to use symbols is the pinnacle of human intelligence, but has yet to be fully replicated in machines. Here we argue that the path towards symbolically fluent artificial intelligence (AI) begins with a reinterpretation of what…
AI systems are increasingly being adopted across various domains and application areas. With this surge, there is a growing research focus and societal concern for actively involving humans in developing, operating, and adopting these…
This paper focuses on the opportunities and the ethical and societal risks posed by advanced AI assistants. We define advanced AI assistants as artificial agents with natural language interfaces, whose function is to plan and execute…
Algorithmic modeling relies on limited information in data to extrapolate outcomes for unseen scenarios, often embedding an element of arbitrariness in its decisions. A perspective on this arbitrariness that has recently gained interest is…
Artificial intelligence (AI) model creators commonly attach restrictive terms of use to both their models and their outputs. These terms typically prohibit activities ranging from creating competing AI models to spreading disinformation.…
As a capability coming from computation, how does AI differ fundamentally from the capabilities delivered by rule-based software program? The paper examines the behavior of artificial intelligence (AI) from engineering points of view to…
Scientists, policy-makers, business leaders, and members of the public care about what modern artificial intelligence systems are disposed to do. Yet terms such as capabilities, propensities, skills, values, and abilities are routinely used…
Assessing an AI system's behavior-particularly in Explainable AI Systems-is sometimes done empirically, by measuring people's abilities to predict the agent's next move-but how to perform such measurements? In empirical studies with humans,…
As artificial intelligence (AI) systems become increasingly complex and ubiquitous, these systems will be responsible for making decisions that directly affect individuals and society as a whole. Such decisions will need to be justified due…
This study investigates malicious AI Assistants' manipulative traits and whether the behaviours of malicious AI Assistants can be detected when interacting with human-like simulated users in various decision-making contexts. We also examine…
Trust has emerged as a key factor in people's interactions with AI-infused systems. Yet, little is known about what models of trust have been used and for what systems: robots, virtual characters, smart vehicles, decision aids, or others.…
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…
A fundamental problem in artificial intelligence is that nobody really knows what intelligence is. The problem is especially acute when we need to consider artificial systems which are significantly different to humans. In this paper we…
As generative foundation models improve, they also tend to become more persuasive, raising concerns that AI automation will enable governments, firms, and other actors to manipulate beliefs with unprecedented scale and effectiveness at…
AI systems are increasingly used in high-stakes domains such as credit rating, where fairness concerns are critical. Existing fairness assessments are typically conducted by AI experts or regulators using predefined protected attributes and…
Numerous parties are calling for the democratisation of AI, but the phrase is used to refer to a variety of goals, the pursuit of which sometimes conflict. This paper identifies four kinds of AI democratisation that are commonly discussed:…
Machine learning (ML) and artificial intelligence (AI) approaches are often criticized for their inherent bias and for their lack of control, accountability, and transparency. Consequently, regulatory bodies struggle with containing this…
The concept of rationality is central to the field of artificial intelligence (AI). Whether we are seeking to simulate human reasoning, or trying to achieve bounded optimality, our goal is generally to make artificial agents as rational as…
Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goals. Progress in this field thus promises to provide greater…