Stanford Seminar - Leveraging Social Theories to Enhance Human-AI Interaction скачать в хорошем качестве

Stanford Seminar - Leveraging Social Theories to Enhance Human-AI Interaction

September 29, 2023 Harman Kaur University of Minnesota Human-AI partnerships are increasingly commonplace. Yet, systems that rely on these partnerships are unable to effectively capture the dynamic needs of people, or explain complex AI reasoning and outputs. The resulting socio-technical gap has led to harmful outcomes such as propagation of biases against marginalized populations and missed edge cases in sensitive domains. My work follows the belief that for human-AI interaction to be effective and safe, technical development in AI must come in concert with an understanding of human-centric cognitive, social, and organizational phenomena. Using human-AI interaction in the context of ML-based decision-support systems as a case study, in this talk, I will discuss my work that explains why interpretability tools do not work in practice. Interpretability tools exacerbate the bounded nature of human rationality, encouraging people to apply cognitive and social heuristics. These heuristics serve as mental shortcuts that make people's decision-making faster by not having to carefully reason about the information being presented. Looking ahead, I will share my research agenda that incorporates social theories to design human-AI systems that not only take advantage of the complementarity between people and AI, but also account for the incompatibilities in how (much) they understand each other. About the speaker: Harman Kaur is an Assistant Professor in the Department of Computer Science and Engineering at the University of Minnesota. Her research areas are human-centered AI, explainability and interpretability, and hybrid intelligence systems. She studies these areas in a variety of domains (e.g., exploratory data analysis, workplace wellbeing and productivity, knowledge search and sensemaking), applying methods towards both critically evaluating existing systems on meeting their intended goals, and designing and building new human-centered systems. She has published several papers at top-tier human-computer interaction venues, such as CHI, CSCW, UIST, and IUI. Her work has won Best Paper Honorable Mention awards at CHI and IUI. Harman received her PhD in both Computer Science and Information from the University of Michigan, and a BS in Computer Science from the University of Minnesota.