Related papers: Tell Me Why: Incentivizing Explanations
Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions. However, as many of these systems are opaque in their operation,…
A multi-level model of opinion formation is presented which takes into account that attitudes on different issues are usually not independent. In the model, agents exchange beliefs regarding a series of facts. A cognitive structure of…
Agents interacting with an incompletely known world need to be able to reason about the effects of their actions, and to gain further information about that world they need to use sensors of some sort. Unfortunately, both the effects of…
Many experiments elicit subjects' prior and posterior beliefs about a random variable to assess how information affects one's own actions. However, beliefs are multi-dimensional objects, and experimenters often only elicit a single response…
Calibration strengthens the trustworthiness of black-box models by producing better accurate confidence estimates on given examples. However, little is known about if model explanations can help confidence calibration. Intuitively, humans…
Adding explanations to recommender systems is said to have multiple benefits, such as increasing user trust or system transparency. Previous work from other application areas suggests that specific user characteristics impact the users'…
Prior work has identified a resilient phenomenon that threatens the performance of human-AI decision-making teams: overreliance, when people agree with an AI, even when it is incorrect. Surprisingly, overreliance does not reduce when the AI…
Modern decision making tools are based on statistical analysis of abundant data, which is often collected by querying multiple individuals. We consider data collection through crowdsourcing, where independent and self-interested agents,…
How to incentivize self-interested agents to explore when they prefer to exploit? Consider a population of self-interested agents that make decisions under uncertainty. They "explore" to acquire new information and "exploit" this…
While a large body of work has scrutinized the meaning of conditional sentences, considerably less attention has been paid to formal models of their pragmatic use and interpretation. Here, we take a probabilistic approach to pragmatic…
Practical mechanisms often limit agent reports to constrained formats like trades or orderings, potentially limiting the information agents can express. We propose a novel class of mechanisms that elicit agent reports in natural language…
We present the notion of explainability for decision-making processes in a pedagogically structured autonomous environment. Multi-agent systems that are structured pedagogically consist of pedagogical teachers and learners that operate in…
Prediction markets elicit and aggregate beliefs by paying agents based on how close their predictions are to a verifiable future outcome. However, outcomes of many important questions are difficult to verify or unverifiable, in that the…
We study the performance of different methods for processing information, incorporating narrative selection within an evolutionary model. All agents update their beliefs according to Bayes' Rule, but some strategically choose the narrative…
Reputation is crucial to enabling human or software agents to select among alternative providers. Although several effective reputation assessment methods exist, they typically distil reputation into a numerical representation, with no…
Appropriate decisions depend on information gathered beforehand, yet such information is often obtained through intermediaries with biased preferences. Motivated by settings such as testing and recertification in organ transplantation, we…
We propose a belief-formation model where agents attempt to discriminate between two theories, and where the asymmetry in strength between confirming and disconfirming evidence tilts beliefs in favor of theories that generate strong (and…
Law codes and regulations help organise societies for centuries, and as AI systems gain more autonomy, we question how human-agent systems can operate as peers under the same norms, especially when resources are contended. We posit that…
Human communication is motivated: people speak, write, and create content with a particular communicative intent in mind. As a result, information that large language models (LLMs) and AI agents process is inherently framed by humans'…
It is well known that reinforcement learning can be cast as inference in an appropriate probabilistic model. However, this commonly involves introducing a distribution over agent trajectories with probabilities proportional to exponentiated…