# Mitigating Biases in Toxic Language Detection through Invariant Rationalization

> Research article (Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021), 2021) · cited 18× · AI/ML

**Wikidata**: [openalex:W3184088840](https://www.wikidata.org/wiki/openalex:W3184088840)  
**Source**: https://4ort.xyz/entity/mitigating-biases-in-toxic-language-detection-through-invariant-rationalization