Research

• Informing agents amidst biased narratives

  Abstract

  I study the strategic interaction between a benevolent sender (who provides data) and a biased narrator (who interprets data) who compete to persuade a boundedly rational receiver (who takes action). The receiver does not know the data-generating model. She chooses between models provided by the sender and the narrator using the maximum likelihood principle, selecting the one that best fits the data given her prior belief. The sender faces a trade-off between providing precise information and minimizing misinterpretation. Surprisingly, full disclosure can be suboptimal and even backfire. I identify a finite set of models that contain the optimal data-generating model, which maximizes the receiver’s expected utility. The sender can guarantee non-negative value of information, preventing harm from misinterpretation. I apply this framework to information campaigns and employee feedback.

• Calibrated Forecasting and Persuasion (with Vianney Perchet) Poster

  (Extended abstract at EC’24)

  Abstract

  We study a dynamic game where an expert sends probabilistic forecasts to a decision-maker. The decision-maker verifies these forecasts using a calibration test based on past data. How should the expert send forecasts to maximize her payoff while passing the test? For a stationary ergodic process, we characterize the optimal forecasting strategy by reducing the dynamic game to a static persuasion problem. The distributions of forecasts that can arise under calibration are precisely the mean-preserving contractions of the distribution of conditionals. We compare the payoffs attainable by an informed and uninformed expert, providing a benchmark for the value of information. Finally, we consider a regret-minimizing decision-maker and show that the expert can always guarantee at least the calibration benchmark and sometimes strictly more.

• Randomization and Efficiency under Incomplete Information (with Itai Arieli, Yakov Babichenko and Rann Smorodinsky) New!

  Abstract

  We study ex-ante Pareto efficiency of feasible outcomes in games with incomplete information. Our main observation is that excessive randomization leads to inefficiency. With a nonatomic prior, generically, efficient outcomes are pure almost surely. In finite state spaces, the restriction is weaker: generically, the total number of actions used across states must be strictly less than the sum of the number of players and states. We apply these results to three environments. In an allocation problem without transfers, the welfare-maximizing incentive-compatible outcome is inefficient. In cheap talk, generically, an outcome is efficient only if it is pure; with state-independent sender payoffs, it is efficient if and only if the sender’s most preferred action is induced with certainty. In Bayesian persuasion with one safe action and several risky actions, outcomes are generically inefficient across broad sets of priors and receiver preferences.

• On the Inefficiency of Social Learning (with Florian Brandl and Wanying (Kate) Huang) New!

  (Extended abstract at EC’26)

  Abstract

  We study whether a social planner can restore efficient learning, defined as a finite expected number of incorrect actions, in the canonical sequential social learning model. For each agent, the planner chooses what social information to disclose and what action-contingent transfer to offer. For unbounded signal distributions with regular tails, we show that whenever learning is inefficient without intervention, no combination of disclosure and transfers can restore efficiency with a finite budget. In particular, disclosure alone cannot restore efficiency. We identify agents' incentives as the key source of this impossibility. The budget requirement, however, concerns the transfers offered rather than the payments made. We show that even under full disclosure, the planner can achieve efficient learning using transfers while keeping expenditure arbitrarily small. Thus, the need for an unlimited budget does not entail large payments.

• Dynamic Cheap Talk without Feedback

  Abstract

  We study a dynamic sender-receiver game in which the sender observes a state evolving according to a Markov chain but does not observe the receiver’s action. Despite the absence of feedback, dynamic interaction partially restores commitment. We show that any equilibrium payoff of a persuasion model with partial commitment—where the sender can deviate to signaling policies that preserve the marginal distribution over messages—can be achieved as a uniform equilibrium payoff in the dynamic game. Moreover, any convex combination of such payoffs across message distributions can also be sustained. When the sender’s payoff is state-independent, she achieves the Bayesian persuasion payoff.