Rejected Dialects: Biases Against African American Language in Reward Models

Summary

This is a publication. If there is no link to the publication on this page, you can try the pre-formated search via the search engines listed on this page.

Authors: Joel Mire, Zubin Trivadi Aysola, Daniel Chechelnitsky, Nicholas Deas, Chrysoula Zerva, Maarten Sap

Journal title: Findings of the Association for Computational Linguistics: NAACL 2025

Journal publisher: Association for Computational Linguistics

Published year: 2025

DOI identifier: 10.18653/V1/2025.FINDINGS-NAACL.417