Towards WinoQueer: Developing a Benchmark for Anti-Queer Bias in Large Language Models. (arXiv:2206.11484v1 [cs.CL])

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

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