# Reward Modeling for Mitigating Toxicity in Transformer-based Language Models

> Research article (arXiv (Cornell University), 2022) · cited 28× · AI/ML

**Wikidata**: [openalex:W4285891774](https://www.wikidata.org/wiki/openalex:W4285891774)  
**Source**: https://4ort.xyz/entity/reward-modeling-for-mitigating-toxicity-in-transformer-based-language-models