Web: http://arxiv.org/abs/2206.11484

June 24, 2022, 1:12 a.m. | Virginia K. Felkner, Ho-Chun Herbert Chang, Eugene Jang, Jonathan May

cs.CL updates on arXiv.org arxiv.org

This paper presents exploratory work on whether and to what extent biases
against queer and trans people are encoded in large language models (LLMs) such
as BERT. We also propose a method for reducing these biases in downstream
tasks: finetuning the models on data written by and/or about queer people. To
measure anti-queer bias, we introduce a new benchmark dataset, WinoQueer,
modeled after other bias-detection benchmarks but addressing homophobic and
transphobic biases. We found that BERT shows significant homophobic bias, …

arxiv benchmark bias language language models large language models models

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY