Jennifer Wortman Vaughan & Hanna Wallach (2021)
Machines We Trust; Perspectives on Dependable AI (MIT Press), 7-32.
Abstract. Vaughan and Wallach's research agenda for intelligible ML — framing interpretability research around concrete stakeholder needs (debugging, accountability, scientific understanding) rather than abstract XAI. The reference cited in policy-aware XAI design.
Tags: ai-usability xai interpretability