Blog posts

Wed 24 January 2024

📄 Undesirable Biases in NLP: Addressing Challenges of Measurement

This post is about our paper "Undesirable Biases in NLP: Addressing Challenges of Measurement", published in JAIR.

Developing tools for measuring & mitigating bias is challenging: LM bias is a complex sociocultural phenomenon and we have no access to a ground truth. We voice our concerns about current bias evaluation practices …

Sun 01 January 2023

Taking a step back and positioning bias: three considerations

In my research, I use various approaches to investigate social bias in language models. When discussing such undesirable biases, we often take a mathematical and 'mechanistic' approach, measuring deviations from a prescriptive norm of ideal behavior (e.g., a skew in gender distribution from 50/50%) or trying to explain …

Thu 14 July 2022

📄 The Birth of Bias: A case study on the evolution of gender bias in an English language model

Language models (LMs) have become essential building blocks of modern AI systems dealing with natural language. These models excel in diverse tasks including sentiment analysis, text generation, translation, and summarization. While their effectiveness stems from neural network architectures trained on vast datasets, this power comes with significant challenges.

Research has …