3 papers
econ.TH2026
A Revealed Preference Framework for AI Alignment
Elchin Suleymanov
Human decision makers increasingly delegate choices to AI agents, raising a natural question: does the AI implement the human principal's preferences or pursue its own? To study th…
econ.TH2025
Robust Maximum Likelihood Updating
Elchin Suleymanov
There is a large body of evidence that decision makers frequently depart from Bayesian updating. This paper introduces a model, robust maximum likelihood (RML) updating, where devi…
econ.TH2025
Entropy Regularized Belief Reporting
Elchin Suleymanov
This paper investigates a model of partition dependence, a widely reported experimental finding where the agent's reported beliefs depend on how the states are grouped. In the mode…