Finale Doshi-Velez & Been Kim (2017)
arXiv preprint.
URL: https://arxiv.org/abs/1702.08608
Abstract. Doshi-Velez and Kim's foundational call for principled interpretability research — distinguishing application-, human-, and functionally-grounded evaluation of explainable AI. Predates and conceptually shapes the most-cited modern XAI methodologies.
Tags: ai-usability xai interpretability foundational