Date: Wednesday, April 23rd, 2025
9:00 am – 10:00 am Pacific Time
12:00 pm – 1:00 pm Eastern Time
Location: Weekly Seminar, Zoom
Title: Relying on the Metrics of Evaluated Agents
Abstract:
Online platforms and regulators face a continuing problem of designing effective evaluation metrics. While tools for collecting and processing data continue to progress, this has not addressed the problem of “unknown unknowns”, or fundamental informational limitations on part of the evaluator. To guide the choice of metrics in the face of this informational problem, we turn to the evaluated agents themselves, who may have more information about how to measure their own outcomes. We model this interaction as an agency game, where we ask: “When does an agent have an incentive to reveal the observability of a metric to their evaluator?” We show that an agent will prefer to reveal metrics that differentiate the most difficult tasks from the rest, and conceal metrics that differentiate the easiest. We further show that the agent can prefer to reveal a metric “garbled” with noise over both fully concealing and fully revealing. This indicates an economic value to privacy that yields Pareto improvement for both the agent and evaluator. We demonstrate these findings on data from online rideshare platforms.
Bio:
Serena is a postdoctoral fellow at Harvard’s Center for Research on Computation and Society (CRCS). Next year, she will be joining UBC as an assistant professor in computer science. She has concurrently collaborated with Google Research at 20% time for the last seven years. Serena received her PhD from UC Berkeley advised by Michael Jordan. Serena’s research is motivated by understanding and improving societal impacts of AI, and recently has been bringing in ideas from economics to model the AI evaluation landscape.