Debiasing GPT-3 Job Ads
Data Skeptic
English - October 10, 2022 13:00 - 48 minutes - 43.6 MB - ★★★★★ - 477 ratingsScience Technology machinelearning datamining datascience science skepticism statistics Homepage Download Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed
Previous Episode: ML Ops in Production
Next Episode: Nano-targetted Facebook Ads
We hear about the impeccable achievements of GPT-3 models, but such large generative models come with their bias. On the show today, Conrad Borchers, a Ph.D. student in Human-Computer Interaction, joins us to discuss the bias in GPT-3 for job ads and how such large models can be de-biased. Listen to learn more!