A brief overview and discussion on gender bias in AI
For International Women’s Day, I wanted to write a short article about gender bias in AI.
AI models reflect, and often exaggerate, existing gender biases from the real world. It is important to quantify such biases present in models in order to properly address and mitigate them.
In this article, I showcase a small selection of important work done (and currently being done) to uncover, evaluate, and measure different aspects of gender bias in AI models. I also discuss the implications of this work and highlight a few gaps I’ve noticed.
All of these terms (”gender”, “bias”, and “AI”) can be somewhat overused and ambiguous.
“Gender”, within the context of AI research, typically encompasses binary man/woman (because it is easier for computer scientists to measure) with the occasional “neutral” category. “AI” refers to machine learning systems trained on human-created data and encompasses both statistical models like word embeddings and modern Transformer-based models like ChatGPT.
Within the context of this article, I refer to “bias” as broadly referring to unequal, unfavorable, and unfair treatment of one group over another.
There are many different ways to categorize, define, and quantify bias, stereotypes, and harms, which is outside the scope of this article. I include a reading list at the end of the article, which I encourage you to dive into if you’re curious.
Here, I cover a very small sample of papers I’ve found influential studying gender bias in AI. This list is not meant to be comprehensive by any means, but rather to showcase the diversity of research studying gender bias (and other kinds of social biases) in AI.
