Abstract: Artificial Intelligence technologies are increasingly used to make decisions and perform autonomous tasks in critical domains such as healthcare, finance, and criminal justice. The needs to understand AI in order to improve, contest, develop appropriate trust and better interact with AI systems have spurred great academic and public interest in Explainable AI (XAI). Recently, open-source toolkits, including IBM Research’s AI Explainability 360, are making a growing collection of XAI techniques into practitioners’ toolbox. My colleagues and I at IBM Research conduct human-computer interaction (HCI) research that aims to empower AI practitioners to make effective and responsible use of such a toolbox to create good XAI user experiences. Meanwhile, our work provides insights into real-world user needs for AI explainability to inform gaps and opportunities for XAI algorithmic research. Our work follows two complementary paths. First, we conduct HCI research by designing and studying XAI systems of various use cases in the AI lifecycle. Second, we study AI design practices of product teams and engage with the design community to develop and advocate for user-centered design processes for XAI. I will conclude the talk with lessons learned for bridging the process of creating responsible AI systems and empowering people in the process.

Speaker Biography: Q. Vera Liao is a Research Staff Member in IBM T.J. Watson Research Center, working in the “Trusted AI” area. Her research background is in human-computer interaction (HCI), with current focuses on human-AI interaction, explainable AI, and conversational agents. Her work received multiple awards at ACM CHI and IUI. She was awarded IBM Outstanding Research Accomplishments for contributions to IBM’s Watson Assistant and Trusted AI toolkits. She serves on the Editorial Board of International Journal of Human-Computer Studies (IJHCS) and ACM Transactions on Interactive Intelligent Systems (TiiS), and the Organizing Committee for CSCW 2021 and IUI 2019. She received a Ph.D. in Computer Science and a M.S. in Human Factors from University of Illinois at Urbana-Champaign, and a bachelor’s degree in Industrial Engineering from Tsinghua University.

RSVP: https://groups.google.com/g/taff-wis-tudelft