Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting

by   Maria De-Arteaga, et al.

We present a large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples' lives. We analyze the potential allocation harms that can result from semantic representation bias. To do so, we study the impact on occupation classification of including explicit gender indicators---such as first names and pronouns---in different semantic representations of online biographies. Additionally, we quantify the bias that remains when these indicators are "scrubbed," and describe proxy behavior that occurs in the absence of explicit gender indicators. As we demonstrate, differences in true positive rates between genders are correlated with existing gender imbalances in occupations, which may compound these imbalances.


Public Perceptions of Gender Bias in Large Language Models: Cases of ChatGPT and Ernie

Large language models are quickly gaining momentum, yet are found to dem...

Gender differences in research grant allocation – a mixed picture

Gender bias in grant allocation is a deviation from the principle that s...

Run Like a Girl! Sports-Related Gender Bias in Language and Vision

Gender bias in Language and Vision datasets and models has the potential...

Are Investors Biased Against Women? Analyzing How Gender Affects Startup Funding in Europe

One of the main challenges of startups is to raise capital from investor...

Uncovering the Source of Machine Bias

We develop a structural econometric model to capture the decision dynami...

Fooling with facts: Quantifying anchoring bias through a large-scale online experiment

Living in the 'Information Age' means that not only access to informatio...

Global method for gender profile estimation from distribution of first names

As social issues related to gender bias attract closer scrutiny, accurat...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset