Related papers: Harmful Random Utility Models
In model-based reinforcement learning, planning with an imperfect model of the environment has the potential to harm learning progress. But even when a model is imperfect, it may still contain information that is useful for planning. In…
Decision-makers often deploy the best-performing treatment from a randomized experiment, creating a winner's curse: selection favors treatments whose observed outcomes are high partly because of statistical noise, so the na\"ive estimate of…
Random Utility Models (RUMs) are a classical framework for modeling user preferences and play a key role in reward modeling for Reinforcement Learning from Human Feedback (RLHF). However, a crucial shortcoming of many of these techniques is…
Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption that better preference ranking translates to better personalized behavior. However, in…
The Competitive Influence Maximization (CIM) problem involves multiple entities competing for influence in online social networks (OSNs). While Deep Reinforcement Learning (DRL) has shown promise, existing methods often assume users'…
Risk assessment algorithms in criminal justice put people's lives at the discretion of a simple statistical tool. This thesis explores how algorithmic decision-making in criminal policy can exhibit feedback effects, where disadvantage…
LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by a one-dimensional subspace, i.e., a refusal direction. In…
We study statistical discrimination of individuals based on payoff-irrelevant social identities in markets that utilize ratings and recommendations for social learning. Even though rating/recommendation algorithms can be designed to be fair…
Humans have come to rely on machines for reducing excessive information to manageable representations. But this reliance can be abused -- strategic machines might craft representations that manipulate their users. How can a user make good…
In this paper, based on a weighted projection of the user-object bipartite network, we study the effects of user tastes on the mass-diffusion-based personalized recommendation algorithm, where a user's tastes or interests are defined by the…
Not all instances in a data set are equally beneficial for inducing a model of the data. Some instances (such as outliers or noise) can be detrimental. However, at least initially, the instances in a data set are generally considered…
LLMs are increasingly used to make or support high-stakes decisions under uncertainty, where alignment depends not only on factual accuracy but on how models weigh tradeoffs between different outcomes. We present an empirical pipeline for…
In online classification, a learner is presented with a sequence of examples and aims to predict their labels in an online fashion so as to minimize the total number of mistakes. In the self-directed variant, the learner knows in advance…
Classification algorithms are increasingly used in areas such as housing, credit, and law enforcement in order to make decisions affecting peoples' lives. These algorithms can change individual behavior deliberately (a fraud prediction…
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…
We consider black-box global optimization of time-consuming-to-evaluate functions on behalf of a decision-maker (DM) whose preferences must be learned. Each feasible design is associated with a time-consuming-to-evaluate vector of…
In many choice settings the decision maker (DM) adopts a criterion which is a mediation between her preference, and its opposite. According to such compromise, the first i alternatives on top of the DM's taste are moved, in reverse order,…
This paper discusses {General Random Utility Models (GRUMs)}. These are a class of parametric models that generate partial ranks over alternatives given attributes of agents and alternatives. We propose two preference elicitation scheme for…
When consequential decisions are informed by algorithmic input, individuals may feel compelled to alter their behavior in order to gain a system's approval. Models of agent responsiveness, termed "strategic manipulation," analyze the…
Recent work in the behavioural sciences has begun to overturn the long-held belief that human decision making is irrational, suboptimal and subject to biases. This turn to the rational suggests that human decision making may be a better…