4 papers
Information Design With Large Language Models
Paul Duetting, Safwan Hossain, Tao Lin +4
Information design is typically studied through the lens of Bayesian signaling, where signals shape beliefs purely based on their correlation with the true state of the world. Howe…
Data-Driven Mechanism Design: Jointly Eliciting Preferences and Information
Dirk Bergemann, Marek Bojko, Paul Dütting +3
We study mechanism design in environments where agents have private preferences and private information about a common payoff-relevant state. In such settings with multi-dimensiona…
A Reduction from Multi-Parameter to Single-Parameter Bayesian Contract Design
Matteo Castiglioni, Junjie Chen, Minming Li +2
The main result of this paper is an almost approximation-preserving polynomial-time reduction from the most general multi-parameter Bayesian contract design (BCD) to single-paramet…
Mechanism Design for Large Language Models
Paul Duetting, Vahab Mirrokni, Renato Paes Leme +2
We investigate auction mechanisms for AI-generated content, focusing on applications like ad creative generation. In our model, agents' preferences over stochastically generated co…