Hila Gonen

Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them

2019 · arXiv (Cornell University)

Word embeddings are widely used in NLP for a vast range of tasks. It was shown that word embeddings derived from text corpora reflect gender biases in society, causing serious concern. Several recent works tackle …

Demystifying Prompts in Language Models via Perplexity Estimation

2023

Language models can be prompted to perform a wide variety of tasks with zero- and few-shot in-context learning. However, performance varies significantly with the choice of prompt, and we do not yet understand why this …