"Reward Modeling for Mitigating Toxicity in Transformer-based Language Models."

Farshid Faal, Ketra A. Schmitt, Jia Yuan Yu (2022)

Details and statistics

DOI:

access: open

type: Informal or Other Publication

metadata version: 2022-05-28

a service of  Schloss Dagstuhl - Leibniz Center for Informatics