Invisibilization as a Source of Probability Bias in Language Models

Language models are aligned to avoid using protected attributes such as race, ethnicity, and gender to inform their responses. Therefore, they increasingly refuse or hedge when such attributes appear in a prompt. However, if a system must decide how much to learn from what people tell it, it is costly to refuse valuable information because of its source. In this article, we measure the cost of…

Publisher's summary from arXiv cs.CL. Read the full article on arXiv cs.CL · More from arXiv cs.CL