Picture for Ketra Schmitt

Ketra Schmitt

Reward Modeling for Mitigating Toxicity in Transformer-based Language Models

Add code
Feb 28, 2022
Figure 1 for Reward Modeling for Mitigating Toxicity in Transformer-based Language Models
Figure 2 for Reward Modeling for Mitigating Toxicity in Transformer-based Language Models
Figure 3 for Reward Modeling for Mitigating Toxicity in Transformer-based Language Models
Figure 4 for Reward Modeling for Mitigating Toxicity in Transformer-based Language Models
Viaarxiv icon