[Adapt] [Seminar] Toxicity in Language Models

[宋秀杰]

Hi Adapters,

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. Thus, in this seminar, I will introduce some methods and analysis about toxicity in LMs. Hope you find it interesting and useful.

Time: Wed 4:00 pm
Venue: SEIEE 3-404

Best regards,
Xiujie Song