We want human preferences to be an objective measure of human values, but this view is not grounded in RLHF practice. Instead, the raters who provide preferences are screened to express certain values and are then trained to provide preferences that adhere to some specific criteria. #FAccT2026
Who's Who of AI
Serena Booth
CS Prof at Brown University, PI of the GIRAFFE lab, former AI Policy Advisor in the US Senate, co-chair of the ACM Tech Policy Subcommittee on AI and Algorithms.
PhD at MIT CSAIL '23, Harvard '16, former Google APM. Dog mom to Ducki.
Their own posts
Recent commentary
Their network
In Serena Booth's orbit
Center = Serena Booth. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.