This article discusses the role of text in visualizations through a study. The focus is on how annotations can shape perceptions of bias and influence predictions. The study uses various…
Continue readingDespite declining to respond to controversial prompts, Large Language Models (LLMs) may still exhibit sociodemographic biases in their latent representations. This study proposes a logistic Bradley Terry probe to detect…
Continue readingThis study investigates if large language models (LLMs) exhibit sociodemographic biases, even when they refuse to respond to sensitive prompts. Researchers explored this by probing contextualized embeddings to see if…
Continue readingThis article investigates the unwanted bias in pretrained vision-and-language (V&L) models, with a focus on gender bias. The authors quantified bias amplification in pretraining and after fine-tuning on three families…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
