Related papers: Value Preferences Estimation and Disambiguation in…

Interactive intelligent systems, i.e., interactive systems that employ AI technologies, are currently present in many parts of our social, public and political life. An issue reoccurring often in the development of these systems is the…

Robot policies need to adapt to human preferences and/or new environments. Human experts may have the domain knowledge required to help robots achieve this adaptation. However, existing works often require costly offline re-training on…

As AI systems increasingly permeate everyday life, designers and developers face mounting pressure to balance innovation with ethical design choices. To date, the operationalisation of AI ethics has predominantly depended on frameworks that…

We consider the challenge of AI value alignment with multiple individuals that have different reward functions and optimal policies in an underlying Markov decision process. We formalize this problem as one of policy aggregation, where the…

AI Safety researchers attempting to align values of highly capable intelligent systems with those of humanity face a number of challenges including personal value extraction, multi-agent value merger and finally in-silico encoding.…

Agreement Technologies refer to open computer systems in which autonomous software agents interact with one another, typically on behalf of humans, in order to come to mutually acceptable agreements. With the advance of AI systems in recent…

We propose a fair machine learning algorithm to model interpretable differences between observed and desired human decision-making, with the latter aimed at reducing disparity in a downstream outcome impacted by the human decision. Prior…

When making decisions, people often overlook critical information or are overly swayed by irrelevant information. A common approach to mitigate these biases is to provide decision-makers, especially professionals such as medical doctors,…

An important feature of pervasive, intelligent assistance systems is the ability to dynamically adapt to the current needs of their users. Hence, it is critical for such systems to be able to recognize those goals and needs based on…

A broad current application of algorithms is in formal and quantitative measures of murky concepts -- like merit -- to make decisions. When people strategically respond to these sorts of evaluations in order to gain favorable decision…

Machine learning based image classification algorithms, such as deep neural network approaches, will be increasingly employed in critical settings such as quality control in industry, where transparency and comprehensibility of decisions…

This paper examines two prominent formal trade-offs in artificial intelligence (AI) -- between predictive accuracy and fairness, and between predictive accuracy and interpretability. These trade-offs have become a central focus in normative…

In the context of computational social choice, we study voting methods that assign a set of winners to each profile of voter preferences. A voting method satisfies the property of positive involvement (PI) if for any election in which a…

Computational preference elicitation methods are tools used to learn people's preferences quantitatively in a given context. Recent works on preference elicitation advocate for active learning as an efficient method to iteratively construct…

Customising AI technologies to each user's preferences is fundamental to them functioning well. Unfortunately, current methods require too much user involvement and fail to capture their true preferences. In fact, to avoid the nuisance of…

As algorithmic tools increasingly aid experts in making consequential decisions, the need to understand the precise factors that mediate their influence has grown commensurately. In this paper, we present a crowdsourcing vignette study…

In approval-based multiwinner voting, voters express approval preferences over a set of candidates, and the goal is to return a winning committee. This model captures a broad range of subset selection problems under preferences. Prior work…

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…

We develop a decision making framework to cast the problem of learning a ranking policy for search or recommendation engines in a two-sided e-commerce marketplace as an expected reward optimization problem using observational data. As a…

Artificial intelligence (AI) is becoming increasingly complex, making it difficult for users to understand how the AI has derived its prediction. Using explainable AI (XAI)-methods, researchers aim to explain AI decisions to users. So far,…