Poster
in
Affinity Workshop: Women in Machine Learning

Political Bias in Neural Retrieval: Model-Agnostic Measurement on Canadian Social Media

Zeynep Pehlivan

Project Page

Abstract

Representational bias inside embedding spaces is a structural property: geometric distortions that persist across tasks and prompts. Because the same vector geometry underlies ranking, classification, clustering, and generation, intrinsic bias can reappear unpredictably at deployment. We study model-agnostic, no-retraining ways to measure and ultimately mitigate such bias in real systems.