Journal Club, episode 7

George shows off the Giant Language Test Room, a web based tool for detecting whether a sample text was generated by BERT or GPT-2. The nifty interface demonstrates that a weakness of these large language models is their predictability.

Lan presents a news item about Setting Fairness Goals with TensorFlow Constrained Optimization Library. This library lets users configure and train machine learning problems based on multiple different metrics, making it easy to formulate and solve many problems of interest to the fairness community.

Kyle: ML Unfairness, Juvenile Recidivism in Catalonia