Measuring and Mitigating Toxicity in LLMs

Building and operating machine learning applications responsibly requires an active, consistent approach to prevent, assess, and mitigate harm. This workshop guides you through how to identify toxicity in traditional and generative AI applications, from understanding the causes and consequences of toxicity to developing and implementing mitigation strategies, including dataset and metric selection.

Security

See CONTRIBUTING for more information.

License

This library is licensed under the MIT-0 License. See the LICENSE file.