If you're deploying LLMs in production, this breaks down concrete techniques for controlling toxic and biased generation—the safety layer that separates a demo from a shippable product.
Large pretrained language models are trained over a sizable collection of online data.
They unavoidably acquire certain toxic behavior and biases from the Internet.
Pretrained language models are very powerful and have shown great success in many NLP tasks.
However, to safely deploy them for practical real-world applications demands a strong safety control over the model generation process.
Transcript
Large pretrained language models are trained over a sizable collection of online data. They unavoidably acquire certain toxic behavior and biases from the Internet. Pretrained language models are very powerful and have shown great success in many NLP tasks. However, to safely deploy them for practical real-world applications demands a strong safety control over the model generation process.
