Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI

An official website of the United States government Here's how you know

Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

This content will become publicly available on June 22, 2027

Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI

Author(s) / Creator(s):: Cheruvu, Aravind; Kanchi, Shravya; M_Abdullah, Sifat; Kong, Nicholas; Yao, Daphne; Jadliwala, Murtuza; Viswanath, Bimal