Rethink reporting of evaluation results in AI
Ryan Burnell, Wout Schellaert, John Burden, Tomer Ullman, Fernando Martínez‐Plumed, Joshua B. Tenenbaum, Danaja Rutar, Lucy G. Cheke, Jascha Sohl‐Dickstein, Melanie Mitchell, Douwe Kiela, Murray Shanahan, Ellen M. Voorhees, Anthony G. Cohn, Joel Z. Leibo, José Hernández‐Orallo
Abstract
Aggregate metrics and lack of access to results limit understanding.
Topics & Concepts
PsychologyComputer scienceComputational biologyBiologyArtificial Intelligence in Healthcare and EducationExplainable Artificial Intelligence (XAI)Ethics and Social Impacts of AI