Hierarchical Detox

On this page, we share additional information and supplementary material on our paper:

Hierarchical Adversarial Correction to Mitigate Identity Term Bias in Toxicity Detection (Schäfer, Heid, Klinger, WASSA-WS 2024)

In this work, we correct the learning of toxicity detection by considering the mentioned targets at different levels of specificity.

Code: https://github.com/Johannes-Schaefer/hierarchical-detox