Skip to content
conftrace_
2024 ICML ICML 2024

Discovering Bias in Latent Space: An Unsupervised Debiasing Approach

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Dyah Adila, SHUAI ZHANG, Boran Han, Bernie Wang

Topics

Artificial Intelligence > Core AI > Interpretability Machine Learning > Core Methods > Representation Learning Deep Learning > Models > Large Language Models

Keywords

latent space instruction-tuned model unlabeled sample spurious association activation value bias direction
Download PDF