Related papers: Should I State or Should I Show? Aligning AI with …
Reinforcement learning (RL) agents optimize only the features specified in a reward function and are indifferent to anything left out inadvertently. This means that we must not only specify what to do, but also the much larger space of what…
Large language models are increasingly used in decision-making tasks that require them to process information from a variety of sources, including both human experts and other algorithmic agents. How do LLMs weigh the information provided…
We seek measurable properties of AI agents that make them better or worse teammates from the subjective perspective of human collaborators. Our experiments use the cooperative card game Hanabi -- a common benchmark for AI-teaming research.…
Smart recommendation algorithms have revolutionized content delivery and improved efficiency across various domains. However, concerns about user agency arise from the algorithms' inherent opacity (information asymmetry) and one-way output…
Recent advances in Large Language Models (LLMs) highlight the need to align their behaviors with human values. A critical, yet understudied, issue is the potential divergence between an LLM's stated preferences (its reported alignment with…
In many real-life settings, algorithms play the role of assistants, while humans ultimately make the final decision. Often, algorithms specifically act as curators, narrowing down a wide range of options into a smaller subset that the human…
Aligning AI systems with human privacy preferences requires understanding individuals' nuanced disclosure behaviors beyond general norms. Yet eliciting such boundaries remains challenging due to the context-dependent nature of privacy…
Large language models (LLMs) are increasingly employed for decision-support across multiple domains. We investigate whether these models display a systematic preferential bias in favor of artificial intelligence (AI) itself. Across three…
A central concern in an interactive intelligent system is optimization of its actions, to be maximally helpful to its human user. In recommender systems for instance, the action is to choose what to recommend, and the optimization task is…
Social media feed algorithms infer user preferences from their past behaviors. Yet what drives engagement often diverges from what users value. We examine this gap between stated preferences (what users say they prefer) and revealed…
System prompts in Large Language Models (LLMs) are predefined directives that guide model behaviour, taking precedence over user inputs in text processing and generation. LLM deployers increasingly use them to ensure consistent responses…
As conversational AI systems become more realistic and widely deployed, users are increasingly uncertain about whether they are interacting with a human or an AI system. When AI identity is unclear, users may unwittingly share sensitive…
Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…
It is challenging to quantify numerical preferences for different objectives in a multi-objective decision-making problem. However, the demonstrations of a user are often accessible. We propose an algorithm to infer linear preference…
As AI agents attempt to autonomously act on users' behalf, they raise transparency and control issues. We argue that permission-based access control is indispensable in providing meaningful control to the users, but conventional permission…
While existing studies have recognised explicit biases in generative models, including occupational gender biases, the nuances of gender stereotypes and expectations of relationships between users and AI companions remain underexplored. In…
Effective human-AI collaboration requires humans to accurately gauge AI capabilities and calibrate their trust accordingly. Humans often have context-dependent private information, referred to as Unique Human Knowledge (UHK), that is…
In decision support applications of AI, the AI algorithm's output is framed as a suggestion to a human user. The user may ignore this advice or take it into consideration to modify their decision. With the increasing prevalence of such…
The integration of users and experts in machine learning is a widely studied topic in artificial intelligence literature. Similarly, human-computer interaction research extensively explores the factors that influence the acceptance of AI as…
We study an extension of the voter model in which each agent is endowed with an innate preference for one of two states that we term as "truth" or "falsehood". Due to interactions with neighbors, an agent that innately prefers truth can be…