Looking For A Handsome Carpenter! Debiasing GPT-3 Job Advertisements

Borchers Conrad, Gala Dalia Sara, Gilburt Benjamin, Oravkin Eduard, Bounsi Wilfried, Asano Yuki M., Kirk Hannah Rose. Arxiv 2022

[Paper]    
Ethics And Bias Fine Tuning GPT Model Architecture Pretraining Methods Prompting RAG Reinforcement Learning Training Techniques

The growing capability and availability of generative language models has enabled a wide range of new downstream tasks. Academic research has identified, quantified and mitigated biases present in language models but is rarely tailored to downstream tasks where wider impact on individuals and society can be felt. In this work, we leverage one popular generative language model, GPT-3, with the goal of writing unbiased and realistic job advertisements. We first assess the bias and realism of zero-shot generated advertisements and compare them to real-world advertisements. We then evaluate prompt-engineering and fine-tuning as debiasing methods. We find that prompt-engineering with diversity-encouraging prompts gives no significant improvement to bias, nor realism. Conversely, fine-tuning, especially on unbiased real advertisements, can improve realism and reduce bias.

Similar Work