Q. Vera Liao (Microsoft Research) – Human-Centered AI Transparency

Transparency—enabling appropriate understanding of AI models or systems—is considered a pillar of Responsible AI. The AI research community and industry have developed an abundance of techniques and artifacts in the hope of achieving transparency, including transparent model reporting, model evaluation, explainable AI (XAI), and communication of model uncertainty. Meanwhile, the human-computer interaction (HCI) community has taken human-centered approaches to these topics, building on its long-standing interests in design to support user understanding and appropriate mental models. In this talk, I will give an overview of common approaches and lessons learned from HCI research on AI transparency. With the recent rise of large language models (LLMs) and LLM-infused systems, I will also reflect on their unique challenges in providing transparency and discuss open questions.