Training LLMs to Self-detoxify Their Language
April 15, 2025
April 15, 2025
CAMBRIDGE, Massachusetts, April 15 -- The Massachusetts Institute of Technology issued the following news:
* * *
Training LLMs to self-detoxify their language
A new method from the MIT-IBM Watson AI Lab helps large language models to steer their own responses toward safer, more ethical, value-aligned outputs.
By Lauren Hinkel, MIT-IBM Watson AI Lab
As we mature from childhood, our vocabulary -- as well as the ways we use it -- grow . . .
* * *
Training LLMs to self-detoxify their language
A new method from the MIT-IBM Watson AI Lab helps large language models to steer their own responses toward safer, more ethical, value-aligned outputs.
By Lauren Hinkel, MIT-IBM Watson AI Lab
As we mature from childhood, our vocabulary -- as well as the ways we use it -- grow . . .