Using Reward Signals to prevent Toxic Responses in LLMs
-
Updated
Sep 2, 2025 - Jupyter Notebook
Using Reward Signals to prevent Toxic Responses in LLMs
Add a description, image, and links to the reward-augmented-decoding topic page so that developers can more easily learn about it.
To associate your repository with the reward-augmented-decoding topic, visit your repo's landing page and select "manage topics."