What is the Role of Social Identity in Large Language Models?

Frontier language models don’t simply generate text. Large language models perform sociocultural sensemaking, drawing on shared cultural patterns (e.g., roles, norms, social identity) to interpret situations and determine appropriate responses. 

This poses a governance problem. Identity can be necessary for ethical and competent judgment in context, yet the dominant paradigm for regulating identity, bias mitigation, treats it mainly as a contaminant to suppress and evaluates systems largely via end outputs. That leaves underspecified how models should decide when identity is relevant, how to reason under uncertainty and unequal power, and how to justify and revise their stance. 

I call this problem bias negotiation: the procedural regulation of identity-conditioned judgments of relevance, inference, and justification. Bias negotiation matters for justice because a positive role for sociocultural reasoning is required to recognize and potentially remediate structural inequities. But it is equally implicated in core model functionality as sociocultural competence is critical in systems that operate across heterogeneous institutions and cultural contexts. Drawing on structured dialogues with multiple deployed chatbots, I identify recurring negotiation repertoires and failure modes, and conclude with specifications that support implementation and procedural evaluation design.

This lecture will also be live streamed via Zoom. You are welcome to join us either in South Hall or online.

For online participants

Online participants must have a Zoom account and be logged in. Sign up for your free account here. If this is your first time using Zoom, please allow a few extra minutes to download and install the browser plugin or mobile app.

Join the lecture online