Preference alignment via reward models helps build safe, helpful, and reliable large language models (LLMs). However, subjectivity in preference judgments and the lack of representative sampling in preference data collection can introduce new biases, hindering reward models' fairness and equity. In this work, we introduce a framework for evaluating dialect biases in reward models and conduct a case study on biases against African American Language (AAL) through several experiments comparing reward model preferences and behavior on paired White Mainstream English (WME) and both machine-translated and human-written AAL corpora. We show that reward models are less aligned with human preferences when processing AAL texts vs. WME ones (-4\% accuracy on average), frequently disprefer AAL-aligned texts vs. WME-aligned ones, and steer conversations toward WME, even when prompted with AAL texts. Our findings provide a targeted analysis of anti-AAL biases at a relatively understudied stage in LLM development, highlighting representational harms and ethical questions about the desired behavior of LLMs concerning AAL.
@article{arxiv.2502.12858,
title = {Rejected Dialects: Biases Against African American Language in Reward Models},
author = {Joel Mire and Zubin Trivadi Aysola and Daniel Chechelnitsky and Nicholas Deas and Chrysoula Zerva and Maarten Sap},
journal= {arXiv preprint arXiv:2502.12858},
year = {2025}
}