
About
Xiao is a Machine Learning research engineer at Google (2019 - present) with a background in Human-Computer Interaction (HCI). She currently works on Large Language Model (LLM) safety and human-ML collaboration.
Most recently, Xiao has been focused on developing new techniques to better align AI systems with principles of human-centered computing and moral reasoning. She has worked extensively on Bard safety evaluation and improvement, training AI systems to assist human raters, and enhancing classifier fairness.
Xiao's prior research focuses on understanding how AI increasingly mediates social exchange and its societal impact on trust. Previously, Xiao worked at Facebook Core Data Science (2018) on trust in social groups and Airbnb (2016) on trust in host profiles.