Related papers: The Wrong Kind of Information
We study how a principal should optimally choose between implementing a new policy and maintaining the status quo when information relevant for the decision is privately held by agents. Agents are strategic in revealing their information;…
Scalable oversight protocols aim to empower evaluators to accurately verify AI models more capable than themselves. However, human evaluators are subject to biases that can lead to systematic errors. We conduct two studies examining the…
Testing the validity of claims made by self-proclaimed experts can be impossible when testing them in isolation, even with infinite observations at the disposal of the tester. However, in a multiple expert setting it is possible to design a…
A natural way of quantifying the ``amount of information'' in decision problems yields a globally concave value for information. Another (in contrast, adversarial) way almost never does.
Computer-use agents have rapidly improved on real-world tasks such as web navigation, desktop automation, and software interaction, in some cases surpassing human performance. Yet even when the task and model are unchanged, an agent that…
In this era of fake news and political polarization, it is desirable to have a system to enable users to access balanced news content. Current solutions focus on top down, server based approaches to decide whether a news article is fake or…
We study the impact of disinformation on a model of resource allocation with independent selfish agents: clients send requests to one of two servers, depending on which one is perceived as offering shorter waiting times. Delays in the…
A model for the joint evolution of opinions and how much the agents trust each other is presented. The model is built using the framework of the Continuous Opinions and Discrete Actions (CODA) model. Instead of a fixed probability that the…
With the spread of false and misleading information in current news, many algorithmic tools have been introduced with the aim of assessing bias and reliability in written content. However, there has been little work exploring how effective…
A sequential decision-making agent balances between exploring to gain new knowledge about an environment and exploiting current knowledge to maximize immediate reward. For environments studied in the traditional literature, optimal…
The survey is concerned with the issue of information transmission from experts to non-experts. Two main approaches to the use of experts can be traced. According to the game-theoretic approach expertise is a case of asymmetric information…
How to optimally persuade an agent who has a private type? When elicitation is feasible, this amounts to a fairly standard principal-agent-style mechanism design problem, where the persuader employs a mechanism to first elicit the agent's…
In some agent designs like inverse reinforcement learning an agent needs to learn its own reward function. Learning the reward function and optimising for it are typically two different processes, usually performed at different stages. We…
A Bayesian agent experiences gain-loss utility each period over changes in belief about future consumption ("news utility"), with diminishing sensitivity over the magnitude of news. Diminishing sensitivity induces a preference over news…
If we could define the set of all bad outcomes, we could hard-code an agent which avoids them; however, in sufficiently complex environments, this is infeasible. We do not know of any general-purpose approaches in the literature to avoiding…
In this paper, we study belief elicitation about an uncertain future event, where the reports will affect a principal's decision. We study two problems that can arise in this setting: (1) Agents may have an interest in the outcome of the…
When agents' information is imperfect and dispersed, existing measures of macroeconomic uncertainty based on the forecast error variance have two distinct drivers: the variance of the economic shock and the variance of the information…
AI systems are often used to make or contribute to important decisions in a growing range of applications, including criminal justice, hiring, and medicine. Since these decisions impact human lives, it is important that the AI systems act…
Our hypothesis is that by equipping certain agents in a multi-agent system controlling an intelligent building with automated decision support, two important factors will be increased. The first is energy saving in the building. The second…
A community of agents is subject to a stream of messages, which are represented as points on a plane of issues. Messages are sent by media and by agents themselves. Messages from media shape the public opinion. They are unbiased, i.e.…