Intersectional Biases in Generative Language Models and Their Psychosocial Impacts
HAI Seminar with Faye-Marie Vassel & Evan Shieh
Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.
Sign Up For Latest News
HAI Seminar with Faye-Marie Vassel & Evan Shieh
Open to Stanford community members! We are hosting an interactive orientation featuring faculty insights, networking, and opportunities to explore AI and data science research, programs, and resources across Stanford.
Open to Stanford community members! We are hosting an interactive orientation featuring faculty insights, networking, and opportunities to explore AI and data science research, programs, and resources across Stanford.
As AI moves beyond language into systems that can perceive, understand, and act in the physical world, a new frontier is emerging: world models—AI systems that build and maintain working representations of real environments to predict how they change in response to action.

As AI moves beyond language into systems that can perceive, understand, and act in the physical world, a new frontier is emerging: world models—AI systems that build and maintain working representations of real environments to predict how they change in response to action.
Sessions run Wednesdays from 4:30–5:30 PM in CoDa E160. Each session features a different Stanford speaker; talk titles are announced by the organizers.

Sessions run Wednesdays from 4:30–5:30 PM in CoDa E160. Each session features a different Stanford speaker; talk titles are announced by the organizers.
Abstract:
The rapid emergence of generative AI technologies has been shaped by a wave of early excitement and hope for a broad range of use cases. Yet, the impacts of the latest models on historically marginalized communities is still relatively understudied, including the potential for sociotechnical harm.
In this session, the speakers present a line of research uncovering intersectional biases in generative language models when they are used for open-ended writing, drawing connections between their synthetic text outputs and known linguistic patterns that have psychosocial impacts for diverse learners in educational settings.

